© 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. 9-GEMMASCOPE-RES-131K
    11. 81319
    Prev
    Next
    INDEX
    Explanations

    phrases indicating capability or sufficiency related to actions or decisions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    enough to do

    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
    Negative Logits
     kasarigan
    -0.65
    queryInterface
    -0.55
     AttributeSet
    -0.52
    \{\\
    -0.48
     Taktlose
    -0.46
    webElementGuid
    -0.45
    oa̍t
    -0.45
    BagLayout
    -0.45
    aarrggbb
    -0.45
     transfieras
    -0.43
    POSITIVE LOGITS
     enough
    1.09
     Enough
    1.02
    Enough
    1.00
    enough
    0.92
    Sufficient
    0.86
     Sufficient
    0.84
     ENOUGH
    0.83
     sufficient
    0.83
     suficiente
    0.75
     fufficient
    0.73
    Activations Density 0.031%

    No Known Activations