© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6934
    Prev
    Next
    INDEX
    Explanations

    personal reflections and statements about experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    keyColumn
    -0.57
    parsedMessage
    -0.53
    ScopeManager
    -0.49
    Heck
    -0.49
    Folks
    -0.48
    HasForeignKey
    -0.45
     aught
    -0.45
     darn
    -0.45
     Heck
    -0.45
     uw
    -0.44
    POSITIVE LOGITS
     fucking
    0.76
     fuckin
    0.73
     [
    0.71
     fucked
    0.68
     weirdly
    0.65
     sort
    0.62
     creatively
    0.56
     fuck
    0.56
     ["
    0.56
    fucking
    0.55
    Activations Density 0.341%

    No Known Activations