© 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. 78873
    Prev
    Next
    INDEX
    Explanations

    proper nouns and important entities within a context

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

    people, names, and roles

    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
    Specifik
    -0.29
     ĝ
    -0.29
     instead
    -0.28
     g
    -0.27
    s
    -0.27
    кій
    -0.27
     Är
    -0.27
    無駄
    -0.26
     d
    -0.26
     Aufenthalt
    -0.26
    POSITIVE LOGITS
     ब्रेकडाउन
    0.99
    SharedDtor
    0.87
    intios
    0.87
     AssemblyCulture
    0.86
     utafitiHapana
    0.83
    tagHelperRunner
    0.82
     Anſ
    0.74
    utilisons
    0.71
     kasarigan
    0.71
     ✭✭
    0.70
    Activations Density 0.108%

    No Known Activations