© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42494
    Prev
    Next
    INDEX
    Explanations

    phrases indicating acceptance or approval

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

    state of being fine

    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
     photography
    -0.42
     a
    -0.40
    refront
    -0.40
     museum
    -0.40
    自ら
    -0.38
     virtual
    -0.37
    ⁣⁣
    -0.36
    să
    -0.36
     highly
    -0.35
    reci
    -0.35
    POSITIVE LOGITS
     okay
    0.73
    alright
    0.68
     OK
    0.67
    okay
    0.64
     alright
    0.64
     OKAY
    0.64
     Okay
    0.63
    Okay
    0.63
     ok
    0.63
     BoxDecoration
    0.62
    Activations Density 0.015%

    No Known Activations