© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 120011
    Prev
    Next
    INDEX
    Explanations

    assertions and claims that suggest relationships or conclusions in the text

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

    reported, showed, proved, suggested

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     queſta
    -0.85
     ſind
    -0.84
    writeFieldEnd
    -0.74
    ValueStyle
    -0.71
    makeConstraints
    -0.69
    IsMutable
    -0.69
     ſei
    -0.69
    quelize
    -0.69
     Efq
    -0.69
    setVerticalGroup
    -0.67
    POSITIVE LOGITS
    ⟭
    0.30
     nécess
    0.30
    ↵↵
    0.28
     ط
    0.28
    <h1>
    0.28
     cuál
    0.27
     viajes
    0.27
     dónde
    0.26
     맞
    0.26
     navegar
    0.26
    Activations Density 0.204%

    No Known Activations