© 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. 9-GEMMASCOPE-RES-131K
    11. 95608
    Prev
    Next
    INDEX
    Explanations

    references to surfaces or materials that have been polished or are in the process of being polished

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

    polish nouns and adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ponses
    -0.45
    createFrom
    -0.45
    BeforeAll
    -0.40
     transmembrane
    -0.39
     Tev
    -0.38
     AppBundle
    -0.38
    StringTo
    -0.38
     receptor
    -0.38
    nextProps
    -0.38
     EventEmitter
    -0.37
    POSITIVE LOGITS
     polish
    1.76
     polishing
    1.64
    polish
    1.58
     Polished
    1.47
    polished
    1.47
     polished
    1.43
    Polish
    1.02
     Polish
    0.96
     pol
    0.84
    pol
    0.84
    Activations Density 0.003%

    No Known Activations