© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3575
    Prev
    Next
    INDEX
    Explanations

    JavaScript constructs related to state management and store creation in Redux

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

    Code-related terms inside React components

    np_acts-logits-general · gemini-2.0-flash

    React and Angular component syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.70
    WebServlet
    -0.65
    DockStyle
    -0.62
     Meksiku
    -0.58
    :✨
    -0.58
    fillText
    -0.57
    buttonBar
    -0.55
    optarg
    -0.54
    cerna
    -0.54
    <!--[
    -0.54
    POSITIVE LOGITS
     useState
    1.26
    useState
    1.16
    useEffect
    0.83
    use
    0.78
     React
    0.72
     use
    0.67
     useEffect
    0.66
    React
    0.65
     useRef
    0.64
    findpost
    0.63
    Activations Density 0.020%

    No Known Activations