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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120848
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Portale
    -0.59
     Hinsicht
    -0.54
     betweenstory
    -0.53
     Infórmanos
    -0.52
    ckså
    -0.52
    ftagPool
    -0.50
    altezza
    -0.47
     TextAppearance
    -0.46
    avía
    -0.46
     desmotivaciones
    -0.46
    POSITIVE LOGITS
     OMITBAD
    0.54
    ///</
    0.53
    providedIn
    0.51
    SourceChecksum
    0.48
     createState
    0.44
    OrBuilder
    0.42
    ActionCreators
    0.42
    FieldNumber
    0.42
    FXML
    0.41
    WithIOException
    0.41
    Activations Density 0.003%

    No Known Activations