Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 5419
    Prev
    Next
    INDEX
    Explanations

    concepts related to monitoring and measuring conditions or compliance

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

    technical, domain-specific keywords—especially high‑information nouns from scientific, engineering, and communications contexts (signals, channels, resources, methods, etc.)

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ाहरण
    -0.76
    帖最后由
    -0.73
    thâu
    -0.72
     <=",
    -0.71
    ThroughAttribute
    -0.66
     Wikimedijinoj
    -0.66
    Jeografia
    -0.64
    EDEFAULT
    -0.62
    省市镇
    -0.62
    putan
    -0.62
    POSITIVE LOGITS
     BoxDecoration
    0.58
    TabIndex
    0.50
    reportWebVitals
    0.49
    unggulan
    0.45
     productor
    0.42
    UnitTesting
    0.42
    AutoresizingMask
    0.42
     initComponents
    0.41
     الاج
    0.41
    izacion
    0.41
    Activations Density 1.263%

    No Known Activations