© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 4719
    Prev
    Next
    INDEX
    Explanations

    elements of JavaScript class components in React

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newState
    -0.35
     unless
    -0.32
     if
    -0.32
     getattr
    -0.31
     resultList
    -0.31
     eventType
    -0.30
     currentState
    -0.29
     SwitchCompat
    -0.28
     inputStream
    -0.27
     columnIndex
    -0.27
    POSITIVE LOGITS
    constructor
    0.97
     async
    0.89
    async
    0.87
     constructor
    0.75
    componentDid
    0.71
    ThroughAttribute
    0.70
    ngOnInit
    0.69
     nakalista
    0.68
    webElement
    0.67
    ConstraintMaker
    0.65
    Activations Density 0.150%

    No Known Activations