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. 114912
    Prev
    Next
    INDEX
    Explanations

    references to legal entities, cases, and statutes

    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
    ftagPool
    -0.65
     SwitchCompat
    -0.63
    XmlEnum
    -0.59
     تانيه
    -0.59
    锈钢
    -0.57
    ConstraintMaker
    -0.55
    Cyfeiriadau
    -0.51
     onCreateView
    -0.50
    webtoken
    -0.50
    shar
    -0.50
    POSITIVE LOGITS
    contentLoaded
    0.37
     cuya
    0.34
    LookAnd
    0.34
     âmes
    0.34
    optarg
    0.34
     asiático
    0.33
     iParam
    0.33
    ACGIH
    0.32
     geweest
    0.32
     Organización
    0.31
    Activations Density 0.030%

    No Known Activations