© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12472
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns, particularly "I" and "he."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows first-person pronouns or common contractions

    np_acts-logits-general · gemini-2.0-flash

    gotta gonna wanna informal speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WireFormatLite
    -0.61
    RegressionTest
    -0.61
     (“
    -0.51
    AntiForgeryToken
    -0.47
     Coats
    -0.47
    propTypes
    -0.46
    ynb
    -0.46
    LLocation
    -0.46
    anair
    -0.45
    uksi
    -0.44
    POSITIVE LOGITS
     gotta
    0.86
     gonna
    0.78
     just
    0.78
     wanna
    0.77
    gotta
    0.75
     kinda
    0.74
    just
    0.70
     dunno
    0.67
    Literally
    0.66
     aint
    0.66
    Activations Density 0.236%

    No Known Activations