© 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. 13-GEMMASCOPE-RES-16K
    6. 8737
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their roles or statements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.54
    :+:
    -0.54
    hyrchwyd
    -0.50
     препратки
    -0.50
     sumpay
    -0.48
     onCancelled
    -0.46
    სქოლიო
    -0.45
     AssemblyCulture
    -0.45
     kasarigan
    -0.44
     ...]
    -0.44
    POSITIVE LOGITS
    الحياه
    0.44
     nahilalakip
    0.38
    AddAttribute
    0.36
     Cardinale
    0.36
    isContained
    0.36
    tagHelperRunner
    0.35
     Piemonte
    0.35
     Ric
    0.34
    PerformLayout
    0.34
     dislikes
    0.34
    Activations Density 1.639%

    No Known Activations