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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14571
    Prev
    Next
    INDEX
    Explanations

    periods within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -1.26
    abestanden
    -1.08
    parsedMessage
    -1.02
    StructEnd
    -0.99
    setVerticalGroup
    -0.99
    Hauptartikel
    -0.96
    LookAnd
    -0.96
     propOrder
    -0.92
    NameInMap
    -0.91
    invokeLater
    -0.90
    POSITIVE LOGITS
     finitely
    0.71
     /\.(
    0.60
     /\.
    0.60
    import
    0.53
     @
    0.51
     gial
    0.50
    @
    0.49
     jakim
    0.48
    zugehen
    0.48
    niaus
    0.48
    Activations Density 0.011%

    No Known Activations