© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12297
    Prev
    Next
    INDEX
    Explanations

    instances of conditional and return statements in programming code

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

    Code snippets and conditional statements

    np_acts-logits-general · gemini-2.0-flash

    code blocks ending with catch statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    IsMutable
    -0.69
    AndEndTag
    -0.69
     surla
    -0.65
    webElementXpaths
    -0.63
    OGND
    -0.62
     gynhyrchwyd
    -0.60
    EndInit
    -0.59
    pushFollow
    -0.59
    Chham
    -0.57
    日閲覧
    -0.57
    POSITIVE LOGITS
    Gew
    0.31
     dot
    0.30
     Кре
    0.30
     cur
    0.29
     SPOT
    0.28
     dott
    0.27
    이며
    0.27
     recours
    0.27
     createState
    0.26
     linearly
    0.26
    Activations Density 0.091%

    No Known Activations