© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2937
    Prev
    Next
    INDEX
    Explanations

    references to individual identity and personal experiences.

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    gender-related discussions and possibly LGBTQ+ content.

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    The main thing this neuron does is find the beginning of first-person statements or observations, particularly those starting with "I" or "And I" or similar phrases like "it was" or "it's". It seems to activate strongly for the start of personal opinions, reflections, or

    oai_token-act-pair · claude-3-5-sonnet-20240620
    Triggered by @bot

    "I" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    I followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     however
    -0.95
    however
    -0.90
    évaluateur
    -0.79
     echter
    -0.77
    However
    -0.76
     jednak
    -0.70
     však
    -0.66
     However
    -0.66
     porém
    -0.65
     però
    -0.64
    POSITIVE LOGITS
     correspondingly
    1.11
     accordingly
    1.10
     consequently
    1.05
    何より
    1.05
     consequent
    0.91
     derfor
    0.87
     frankly
    0.87
     certainly
    0.85
     dermed
    0.85
     соответственно
    0.84
    Activations Density 0.235%

    No Known Activations