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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 358
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and court procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedModule
    -0.38
    ksamkeit
    -0.38
    ôts
    -0.38
    grunns
    -0.37
    illig
    -0.37
     sjø
    -0.36
    tablissements
    -0.36
     kveld
    -0.36
     industriels
    -0.36
     sätt
    -0.35
    POSITIVE LOGITS
    BeginContext
    0.81
    новништво
    0.69
    клопе
    0.62
    SharedCtor
    0.59
    uxxxx
    0.58
    addGap
    0.56
    mtrl
    0.55
    GOTREF
    0.54
    CharacterOffset
    0.53
     surla
    0.52
    Activations Density 0.774%

    No Known Activations