© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1361
    Prev
    Next
    INDEX
    Explanations

    terms related to variety and breadth in contexts

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

    "Wide" or "broader" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    wide range or variety

    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
     cucchia
    -0.47
    checkpoint
    -0.44
    UnsafeEnabled
    -0.44
    MigrationBuilder
    -0.43
     CGPoint
    -0.43
     jSON
    -0.42
     typelib
    -0.41
    CGPoint
    -0.41
     MATTER
    -0.40
    Билгалдахарш
    -0.40
    POSITIVE LOGITS
     Wide
    1.10
     wide
    1.09
    Wide
    1.04
     widest
    1.02
     geniş
    0.95
     WIDE
    0.94
     breadth
    0.94
    wide
    0.93
     broadest
    0.93
     broad
    0.91
    Activations Density 0.219%

    No Known Activations