© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1318
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions and comparisons in data

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

    Preceding approximate quantities

    np_acts-logits-general · gemini-2.0-flash

    approximation and comparison numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.47
    存于互联网档案馆
    -0.44
     AssemblyCulture
    -0.44
     HasFactory
    -0.42
    IsPostBack
    -0.40
    enschutzer
    -0.40
    WithIdentifier
    -0.38
    currentColor
    -0.37
    writeFieldEnd
    -0.37
    艋
    -0.37
    POSITIVE LOGITS
     nearly
    0.73
    nearly
    0.67
    expandindo
    0.65
    выше
    0.64
    Nearly
    0.63
     Nearly
    0.63
    addGap
    0.61
    nigh
    0.58
     whopping
    0.57
     AssemblyVersion
    0.56
    Activations Density 0.208%

    No Known Activations