© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 9319
    Prev
    Next
    INDEX
    Explanations

    code or syntax elements in programming languages

    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
    Tembelea
    -0.68
     resultCode
    -0.62
     userSchema
    -0.61
     виправивши
    -0.57
    DebuggerNonUser
    -0.54
    })$}
    -0.54
    setScene
    -0.50
    dega
    -0.49
    Salta
    -0.48
    TypedDataSet
    -0.48
    POSITIVE LOGITS
    ↵↵
    0.94
    NOPQRST
    0.67
    genossen
    0.57
     ogóle
    0.54
    gameserver
    0.53
     médec
    0.52
    éről
    0.52
    ResumeLayout
    0.51
     ModelExpression
    0.51
     Majefty
    0.50
    Activations Density 0.665%

    No Known Activations