© 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. 2-GEMMASCOPE-RES-16K
    6. 12846
    Prev
    Next
    INDEX
    Explanations

    terms related to nerves and nerve-related medical procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.41
     contag
    -0.37
     vœ
    -0.36
     Kelas
    -0.35
     assets
    -0.35
     assumptions
    -0.35
     skai
    -0.35
     invokingState
    -0.34
     nahilalakip
    -0.34
     escen
    -0.34
    POSITIVE LOGITS
     Bra
    0.84
     bra
    0.83
     pe
    0.76
    Bra
    0.75
    TagMode
    0.73
    bra
    0.72
     Bracket
    0.68
    ko
    0.66
    eta
    0.65
     brackets
    0.62
    Activations Density 0.182%

    No Known Activations