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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 12674
    Prev
    Next
    INDEX
    Explanations

    references to fandom and personal enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the phrase "a huge fan" and related expressions of enthusiasm or fandom.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    页面存档备份
    -0.34
    RenderAtEndOf
    -0.32
     placas
    -0.32
    IVEREF
    -0.30
     necesit
    -0.30
    lepiej
    -0.30
     voren
    -0.28
    spě
    -0.28
     efficacement
    -0.28
     <>",
    -0.28
    POSITIVE LOGITS
     fans
    2.30
     fan
    2.19
     Fans
    1.91
    fans
    1.88
    Fans
    1.81
    fan
    1.63
    ファン
    1.56
     fãs
    1.52
     Fan
    1.52
    Fan
    1.50
    Activations Density 0.145%

    No Known Activations