© 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. 78632
    Prev
    Next
    INDEX
    Explanations

    fragments of data, references to people, and specific identifiers in a document

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

    long s characters

    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
    rungsseite
    -0.45
     nahilalakip
    -0.44
    endregion
    -0.41
     j
    -0.40
    تقاوى
    -0.40
     بيها
    -0.38
    ciorys
    -0.37
     estekak
    -0.37
    parseFrom
    -0.35
    ArrowToggle
    -0.34
    POSITIVE LOGITS
     raiſ
    0.66
     faſt
    0.65
     ſte
    0.60
     ſever
    0.58
     ſtill
    0.57
     EconPapers
    0.56
     enfans
    0.56
     ſtand
    0.55
     ſou
    0.52
     unſ
    0.52
    Activations Density 0.066%

    No Known Activations