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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 14087
    Prev
    Next
    INDEX
    Explanations

    programming constructs and definitions related to header files in coding

    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
    hadapi
    -0.36
     Infantil
    -0.34
    samples
    -0.33
     carrier
    -0.32
     convene
    -0.32
     tra
    -0.32
     Púb
    -0.32
     drink
    -0.32
     carriers
    -0.31
    infer
    -0.31
    POSITIVE LOGITS
    LElement
    0.57
    verwijspagina
    0.56
    ngdoc
    0.52
     Duplicate
    0.52
    :✨
    0.52
    RectangleBorder
    0.51
    帖最后由
    0.51
    hdashline
    0.50
    abestanden
    0.49
    Twice
    0.49
    Activations Density 0.566%

    No Known Activations