© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1461
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific AST (Abstract Syntax Tree) node types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hobo
    -0.65
     Tijuana
    -0.62
     Murad
    -0.60
    RenderAtEndOf
    -0.59
    licken
    -0.59
    herb
    -0.58
     Snapdragon
    -0.58
     californ
    -0.57
     Wolverine
    -0.56
     Wenger
    -0.56
    POSITIVE LOGITS
    ast
    2.83
     ast
    2.47
     Ast
    2.47
    Ast
    2.36
     AST
    2.21
    AST
    2.18
     astro
    1.63
    asts
    1.59
     Astro
    1.58
    astro
    1.53
    Activations Density 0.114%

    No Known Activations