© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1273
    Prev
    Next
    INDEX
    Explanations

    references to medical or nutritional properties of substances

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

    Enumerated lists or parenthetical statements

    np_acts-logits-general · gemini-2.0-flash

    list item separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     autorytatywna
    -0.83
     חיצוניים
    -0.81
    səhifə
    -0.77
    migrationBuilder
    -0.73
    ########.
    -0.70
    addGap
    -0.70
     EconPapers
    -0.69
     surla
    -0.68
    NgModule
    -0.68
    ementara
    -0.68
    POSITIVE LOGITS
    ↵↵
    0.48
    ↵
    0.37
     and
    0.34
     Additionally
    0.32
     Also
    0.31
     Furthermore
    0.30
     By
    0.30
     If
    0.30
     etc
    0.29
     AND
    0.29
    Activations Density 0.167%

    No Known Activations