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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27228
    Prev
    Next
    INDEX
    Explanations

    specific structural elements or conditions relevant to a technical or scientific context

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

    fields. unportable

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects tokens that introduce or point to important statements or key content (words that mark results, topics, or clause-leading discourse markers).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    aarrggbb
    -0.77
     nakalista
    -0.69
    tagHelperRunner
    -0.67
    脚注の使い方
    -0.67
    IntoConstraints
    -0.66
    ftagPool
    -0.65
    transQ
    -0.63
    Datuak
    -0.61
    rungsseite
    -0.60
     pinulongan
    -0.60
    POSITIVE LOGITS
     indépend
    0.31
     CHAP
    0.31
    bud
    0.29
    Mobil
    0.29
     tank
    0.29
    CHAP
    0.29
    DateTimeField
    0.28
    sm
    0.28
     Kip
    0.28
    pi
    0.28
    Activations Density 0.927%

    No Known Activations