© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 63379
    Prev
    Next
    INDEX
    Explanations

    phrases related to metrics, measurements, or statistical comparisons

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

    comparisons of size and quantity

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    StoreMessageInfo
    -0.59
    httphttps
    -0.57
     EconPapers
    -0.54
    jamientos
    -0.46
     Hoffnung
    -0.46
    IActionResult
    -0.44
    chauung
    -0.44
    TypedDataSet
    -0.44
    火
    -0.43
     getItemId
    -0.42
    POSITIVE LOGITS
    sizeCache
    0.44
    posedge
    0.41
    onActivityResult
    0.39
     stubborn
    0.38
    parseColor
    0.37
    stateProvider
    0.37
    HtmlAttribute
    0.36
     heavier
    0.36
    WithFormat
    0.35
     itinéraires
    0.35
    Activations Density 0.237%

    No Known Activations