Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53814
    Prev
    Next
    INDEX
    Explanations

    characters and symbols often used in coding or gaming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     surla
    -0.85
    InputTagHelper
    -0.81
    UnknownFieldSet
    -0.80
    AnchorTagHelper
    -0.78
    RenderAtEndOf
    -0.77
    PreferredItem
    -0.75
     utafitiHapana
    -0.71
     المعيارى
    -0.70
    AutoField
    -0.69
    migrationBuilder
    -0.66
    POSITIVE LOGITS
    Werdegang
    0.35
     bocetos
    0.32
    Спасылкі
    0.29
     normalidad
    0.29
     nonUne
    0.28
     kemarin
    0.28
     embarc
    0.26
    GEBURTSDATUM
    0.26
     desbloquear
    0.26
    ñores
    0.26
    Activations Density 0.008%

    No Known Activations