© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 53661
    Prev
    Next
    INDEX
    Explanations

    specific names of orchestras and musical compositions

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

    Columbus Symphony Orchestra

    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
    MigrationBuilder
    -1.15
    webElementXpaths
    -1.11
    featureID
    -1.05
    aarrggbb
    -0.94
     resourceCulture
    -0.85
    帖最后由
    -0.83
     propOrder
    -0.81
    XMLSchema
    -0.78
     Италијани
    -0.76
    новништво
    -0.75
    POSITIVE LOGITS
     and
    0.40
     E
    0.36
    Runtime
    0.35
     Clo
    0.34
     culture
    0.32
     R
    0.32
    …
    0.32
     Garden
    0.31
     Nan
    0.31
     Bat
    0.31
    Activations Density 0.234%

    No Known Activations