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. 12452
    Prev
    Next
    INDEX
    Explanations

    instances and structures of loops or iterations in code

    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
     kaarangay
    -0.54
    (__('
    -0.52
    onedDateTime
    -0.51
     ujednoznacz
    -0.47
    addCriterion
    -0.47
    olverine
    -0.46
    transQ
    -0.45
     Brem
    -0.44
     Olympic
    -0.44
    internalType
    -0.44
    POSITIVE LOGITS
    AnchorStyles
    0.63
    forEach
    0.56
    foreach
    0.56
     defaultstate
    0.55
    for
    0.54
    every
    0.51
    ForAll
    0.48
    Every
    0.48
    AlterField
    0.48
    zość
    0.47
    Activations Density 0.133%

    No Known Activations