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. 8223
    Prev
    Next
    INDEX
    Explanations

    terms and structures related to programming, particularly in the context of managing and manipulating memory and data 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
    KommentareTeilen
    -0.56
    AndEndTag
    -0.51
    ArgsConstructor
    -0.45
    omitempty
    -0.44
    VersionUID
    -0.42
     שוליים
    -0.42
     pinulongan
    -0.42
    EDEFAULT
    -0.41
    sal
    -0.40
    argout
    -0.40
    POSITIVE LOGITS
     ProtoMessage
    0.60
    gonic
    0.56
    tanleria
    0.51
    IntoConstraints
    0.45
     HFILL
    0.45
    INSTALLED
    0.45
    SourceChecksum
    0.42
    المكان
    0.41
     Reſ
    0.40
     NACIONAL
    0.40
    Activations Density 0.038%

    No Known Activations