© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 568
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and data structure definitions

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

    variable and function names in code that contain underscores or are part of camelCase identifiers.

    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
    ’
    -0.36
    ANSA
    -0.36
    -
    -0.35
    ス
    -0.34
     Pfeffer
    -0.33
     zza
    -0.33
     norte
    -0.33
     Senator
    -0.33
     Scott
    -0.32
     Schmidt
    -0.32
    POSITIVE LOGITS
    pecabe
    0.90
     betweenstory
    0.84
    ſchaft
    0.78
    iſen
    0.75
    iſchen
    0.75
    iſche
    0.75
    iſten
    0.74
    mpagne
    0.74
    ロウィン
    0.72
    chränk
    0.72
    Activations Density 0.385%

    No Known Activations