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. 379
    Prev
    Next
    INDEX
    Explanations

    patterns of numerical data and sequences

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

    patterns resembling decimal numbers or numeric sequences with decimals.

    oai_token-act-pair · gpt-4oTriggered 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
     casque
    -0.52
    ULOS
    -0.49
    ubre
    -0.46
    catching
    -0.45
    ensore
    -0.43
    caccio
    -0.42
    chae
    -0.42
    ⓧ
    -0.42
    yield
    -0.42
    setStroke
    -0.41
    POSITIVE LOGITS
    ViewFeatures
    1.01
    ThroughAttribute
    0.82
    enterOuterAlt
    0.81
     nahilalakip
    0.77
    makeText
    0.76
     AssemblyProduct
    0.76
    RuleContext
    0.72
     cherchés
    0.72
    sizeCache
    0.71
     生命周期
    0.69
    Activations Density 0.997%

    No Known Activations