Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114520
    Prev
    Next
    INDEX
    Explanations

    symbols and syntax associated with programming and configuration settings

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

    Code comments that provide metadata, documentation, or explanatory notes about the surrounding code across various programming languages.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.46
     Meksiku
    -0.43
     pregă
    -0.40
     uwag
    -0.39
     propOrder
    -0.39
    jsxFileName
    -0.37
    OGND
    -0.36
     Chwiliwch
    -0.35
    舺
    -0.35
     ragaz
    -0.35
    POSITIVE LOGITS
    LookAnd
    0.60
    RegressionTest
    0.58
    .*")]
    0.52
    MathML
    0.49
    ViewImports
    0.46
    ErrUnexpectedEOF
    0.45
     виправивши
    0.45
     enco
    0.44
    ***************/
    0.43
    ]")]
    0.42
    Activations Density 0.293%

    No Known Activations