© 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. 14978
    Prev
    Next
    INDEX
    Explanations

    conditional statements and expressions in programming contexts

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

    Code snippets with specific color variables

    np_acts-logits-general · gemini-2.0-flash

    color and graphics commands

    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
     houſe
    -0.44
     ennemi
    -0.37
     Houſe
    -0.36
    arrêter
    -0.35
     laſt
    -0.35
    arriver
    -0.33
     mourut
    -0.32
     évêque
    -0.32
     noires
    -0.32
    atteindre
    -0.31
    POSITIVE LOGITS
    RetentionPolicy
    0.79
    __(/*!
    0.73
    thenReturn
    0.70
    __*/
    0.68
    arakhand
    0.67
     defaultstate
    0.67
    makeText
    0.65
     ſehr
    0.65
     ویکی‌پدیای
    0.63
    arangay
    0.63
    Activations Density 0.099%

    No Known Activations