© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 3400
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hit" and its related forms, emphasizing physical contact or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🔹
    -0.74
     defaultValue
    -0.68
    defaultValue
    -0.67
    הערות
    -0.64
     généraux
    -0.64
     undangan
    -0.62
    categoryName
    -0.62
    nisk
    -0.61
    ordinaire
    -0.60
    Procedimiento
    -0.60
    POSITIVE LOGITS
     hit
    2.30
     Hit
    2.18
    Hit
    2.17
     hits
    2.14
     HIT
    2.14
    hit
    2.11
     hitting
    2.02
    HIT
    1.99
     Hits
    1.96
    hits
    1.81
    Activations Density 0.044%

    No Known Activations