Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7473
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical actions or movements

    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
    ❋
    -0.42
    VersionUID
    -0.39
    occupe
    -0.38
    कड
    -0.38
     الرحمن
    -0.38
    Kariera
    -0.37
    genommen
    -0.36
    wka
    -0.36
    boxShadow
    -0.35
    rinfo
    -0.35
    POSITIVE LOGITS
     its
    0.79
     your
    0.73
     svůj
    0.68
     अपना
    0.68
     swoje
    0.64
     svou
    0.61
     своё
    0.61
     अपनी
    0.61
     swój
    0.59
    自己的
    0.57
    Activations Density 0.859%

    No Known Activations