© 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. 126831
    Prev
    Next
    INDEX
    Explanations

    phrases related to filtering and processing information in a technical context

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

    technical or numerical contexts

    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
    J
    -0.27
     Bezir
    -0.25
     Daerah
    -0.25
     Sternen
    -0.24
     
    -0.24
     run
    -0.23
    set
    -0.23
     Chisholm
    -0.23
    am
    -0.23
     set
    -0.23
    POSITIVE LOGITS
    tagHelperRunner
    1.02
    OGND
    0.98
     estekak
    0.95
     queſta
    0.90
    ementara
    0.90
    IsMutable
    0.89
     Chwiliwch
    0.85
    parsedMessage
    0.84
    richTextPanel
    0.84
    MigrationBuilder
    0.84
    Activations Density 0.000%

    No Known Activations