© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 459
    Prev
    Next
    INDEX
    Explanations

    JavaScript functions and method calls related to data fetching and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    calls to the useEffect hook and related asynchronous data-fetching patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.86
    tanleria
    -0.66
    Insee
    -0.63
    endpush
    -0.62
     Cæsar
    -0.59
     StatelessWidget
    -0.59
    SourceChecksum
    -0.57
    aarrggbb
    -0.56
    prepareStatement
    -0.56
    cloths
    -0.56
    POSITIVE LOGITS
    ArgsConstructor
    2.45
     useEffect
    1.74
    useEffect
    1.71
    ScopeManager
    1.56
    CloseOperation
    0.94
    ParallelGroup
    0.91
    FromArgb
    0.88
    JoinColumn
    0.83
     noqa
    0.79
     JAXBElement
    0.73
    Activations Density 0.015%

    No Known Activations