© 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-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7400
    Prev
    Next
    INDEX
    Explanations

    instances of the word "walk" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.75
    dieu
    -0.61
    \{\\
    -0.57
    RetentionPolicy
    -0.57
    영어
    -0.56
     dramatic
    -0.56
    tablir
    -0.54
     Petit
    -0.54
    UTIVE
    -0.54
    reicher
    -0.53
    POSITIVE LOGITS
     walks
    1.17
    walks
    1.14
     walk
    1.08
     walked
    1.06
    walk
    1.05
     walking
    0.99
    Walk
    0.99
     WALK
    0.97
    walking
    0.89
    Walking
    0.89
    Activations Density 0.154%

    No Known Activations