© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 12980
    Prev
    Next
    INDEX
    Explanations

    code comments and conditional preprocessor directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posób
    -0.61
    TokenNameLPAREN
    -0.57
    !("{}",
    -0.57
     FontWeight
    -0.56
     Hartman
    -0.56
     ?>>
    -0.56
    nestjs
    -0.53
    stdafx
    -0.52
     Injectable
    -0.51
     Mullins
    -0.51
    POSITIVE LOGITS
     nakalista
    0.86
     للمعارف
    0.74
     متعلقه
    0.74
     ModelExpression
    0.73
     виправивши
    0.71
     оригіналу
    0.69
     שוליים
    0.69
    Clik
    0.68
     insuffisamment
    0.68
    رشف
    0.68
    Activations Density 0.063%

    No Known Activations