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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 131037
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to organizations and their hierarchical structures

    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
    routeProvider
    -0.64
    KURZBESCHREIBUNG
    -0.63
    UrlResolution
    -0.61
     Chwiliwch
    -0.60
     surla
    -0.55
    UnsafeEnabled
    -0.55
     Brum
    -0.53
    HandlerContext
    -0.52
    delwed
    -0.52
     nahilalakip
    -0.52
    POSITIVE LOGITS
    +#+
    0.38
    writeField
    0.30
     שוליים
    0.26
    (
    0.26
    Rgb
    0.25
    育
    0.25
    #+#
    0.25
     روز
    0.24
     fuma
    0.24
    といって
    0.24
    Activations Density 0.264%

    No Known Activations