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. 21-GEMMASCOPE-RES-16K
    6. 7251
    Prev
    Next
    INDEX
    Explanations

    references to data access and personal information privacy concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CHOOSE
    -0.37
     COLLECT
    -0.35
    Collected
    -0.34
     aprendido
    -0.32
     приня
    -0.30
    ACCEPTED
    -0.29
    gü
    -0.29
    欽
    -0.29
     plagio
    -0.29
     approximation
    -0.29
    POSITIVE LOGITS
    InjectAttribute
    0.71
     disambiguazione
    0.67
     autorytatywna
    0.61
     ProtoMessage
    0.56
    ViewImports
    0.56
     databases
    0.55
     mergeFrom
    0.53
     searches
    0.53
     queries
    0.51
    nss
    0.51
    Activations Density 0.365%

    No Known Activations