© 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. 22-GEMMASCOPE-RES-16K
    11. 8066
    Prev
    Next
    INDEX
    Explanations

    components and configurations related to software libraries and their linking processes

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

    Code-related terms (compilation, linking, build)

    np_acts-logits-general · gemini-2.0-flash

    build command statements

    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
    boer
    -0.48
    fromCharCode
    -0.46
     ranch
    -0.45
    paddingVertical
    -0.44
     ан
    -0.43
     Gartner
    -0.42
    кове
    -0.42
    ην
    -0.42
     Ranch
    -0.42
    bgp
    -0.41
    POSITIVE LOGITS
    تقاوى
    0.77
    oredCriteria
    0.72
     Build
    0.67
    ThroughAttribute
    0.66
    writeFieldEnd
    0.64
     Builds
    0.64
     build
    0.64
     resourceCulture
    0.64
    build
    0.63
    Build
    0.62
    Activations Density 0.806%

    No Known Activations