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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12396
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-reflection and personal growth

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

    Followed by a past-tense verb

    np_acts-logits-general · gemini-2.0-flash

    past tense verb completions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currently
    -0.69
    currently
    -0.67
     Currently
    -0.65
     are
    -0.63
     actuellement
    -0.63
     bislang
    -0.62
     છે
    -0.61
     nincs
    -0.61
    Currently
    -0.61
     atualmente
    -0.61
    POSITIVE LOGITS
     was
    1.91
     were
    1.27
     did
    1.23
     had
    1.23
     wasn
    1.21
     gave
    1.15
     lacked
    1.13
     consisted
    1.13
     didn
    1.12
     vardı
    1.12
    Activations Density 9.992%

    No Known Activations