© 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. 35-GEMMASCOPE-RES-16K
    11. 7634
    Prev
    Next
    INDEX
    Explanations

    phrases indicating rationale or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    multer
    -0.46
    دانشنامهٔ
    -0.44
    Jîn
    -0.42
    dengan
    -0.39
    djangoproject
    -0.39
    Попис
    -0.38
    cotch
    -0.37
    ASKET
    -0.36
    󠁬
    -0.36
    󠁮
    -0.35
    POSITIVE LOGITS
     why
    0.97
    why
    0.70
     mengapa
    0.68
     warum
    0.64
     kenapa
    0.63
     Reason
    0.62
     WHY
    0.62
     behind
    0.59
     reason
    0.58
     waarom
    0.56
    Activations Density 0.240%

    No Known Activations