© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3988
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a forceful or assertive action

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

    "push" and its variations

    np_acts-logits-general · gemini-2.0-flash

    pushing against or forward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasForeignKey
    -0.34
     ***!
    -0.32
    
    -0.32
    الدراسه
    -0.31
    جوايز
    -0.30
    isnan
    -0.29
     neemt
    -0.29
     genieten
    -0.29
    StatusOK
    -0.28
     Winaray
    -0.28
    POSITIVE LOGITS
     pushes
    1.48
     pushing
    1.46
     push
    1.46
     Pushing
    1.44
     pushed
    1.44
    Pushing
    1.41
    pushed
    1.39
     PUSH
    1.38
     Push
    1.37
    Push
    1.30
    Activations Density 0.167%

    No Known Activations