© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13897
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a broad range or variety of subjects

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

    "wide" or its translation

    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-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
     jSON
    -0.50
    computa
    -0.48
    checkpoint
    -0.47
     napkins
    -0.46
     getItem
    -0.46
    PathParam
    -0.44
    ModelAdmin
    -0.44
     LoginPage
    -0.41
     ViewController
    -0.41
     pellic
    -0.41
    POSITIVE LOGITS
     wide
    1.21
     Wide
    1.20
    Wide
    1.17
    wide
    1.13
     WIDE
    1.02
    WIDE
    0.97
     geniş
    0.96
     widest
    0.95
     broad
    0.94
     breite
    0.94
    Activations Density 0.070%

    No Known Activations