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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4233
    Prev
    Next
    INDEX
    Explanations

    code structures, specifically brackets and function calls in programming languages

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

    Follows a number

    np_acts-logits-general · gemini-2.0-flash

    technical and localized content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igh
    -0.42
    $\\
    -0.39
    Norman
    -0.38
    ough
    -0.38
    <sup>
    -0.38
    振
    -0.38
    Advisor
    -0.36
    夫
    -0.36
     Regen
    -0.35
    ukan
    -0.35
    POSITIVE LOGITS
    Hauptartikel
    1.07
    ConstraintMaker
    0.95
    enterOuterAlt
    0.91
     resourceCulture
    0.85
    StoryboardSegue
    0.84
    principalColumn
    0.83
    IndentedString
    0.82
    WebVitals
    0.80
    Personendaten
    0.80
    клопе
    0.80
    Activations Density 0.106%

    No Known Activations