© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104482
    Prev
    Next
    INDEX
    Explanations

    interrogative words and phrases related to questions and inquiries

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

    Interrogative words and phrases that define context parameters (when, where, how, what, why) particularly in technical or structured text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    BeginContext
    -0.41
     fil
    -0.35
    CrossRef
    -0.34
     bin
    -0.33
    calaure
    -0.31
     dim
    -0.30
     LayoutInflater
    -0.30
     GetEnumerator
    -0.30
    databinding
    -0.30
    binom
    -0.30
    POSITIVE LOGITS
     missão
    0.57
    SBATCH
    0.57
     betweenstory
    0.56
     ligiloj
    0.55
    __':
    0.55
    ThemeOverlay
    0.55
    queryInterface
    0.54
    writeFieldEnd
    0.53
    LookAnd
    0.51
    IntoConstraints
    0.51
    Activations Density 0.165%

    No Known Activations