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. 41-GEMMASCOPE-RES-16K
    6. 7107
    Prev
    Next
    INDEX
    Explanations

    character interactions and emotional expressions in dialogue

    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
    AccessorTable
    -0.52
     felt
    -0.46
    :✨
    -0.45
     creș
    -0.44
     feels
    -0.43
     فريبيس
    -0.42
    vum
    -0.42
     siente
    -0.42
     Feels
    -0.40
     voelt
    -0.40
    POSITIVE LOGITS
     gest
    0.68
     motion
    0.66
     dramatically
    0.60
     ges
    0.58
     theat
    0.56
     waving
    0.56
     brand
    0.55
     wag
    0.55
     motions
    0.53
     pointing
    0.52
    Activations Density 0.258%

    No Known Activations