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. 10-GEMMASCOPE-RES-16K
    6. 3093
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities in informal contexts, often within conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.59
     estekak
    -0.57
    
    -0.55
    URLException
    -0.55
    ">//
    -0.55
     dAtA
    -0.54
     Wikimedijinoj
    -0.53
    esez
    -0.53
    aarrggbb
    -0.53
    BrowserRouter
    -0.52
    POSITIVE LOGITS
     autorytatywna
    0.73
    ArgsConstructor
    0.65
    PropertyChanging
    0.54
    Население
    0.51
     CoreData
    0.51
    InSection
    0.50
    autoIncrement
    0.49
    assertj
    0.48
    useEffect
    0.46
    twimg
    0.46
    Activations Density 8.322%

    No Known Activations