© 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. 42696
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and expressions related to processes and effects

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

    competitive globally

    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
    Negative Logits
    InitVars
    -0.61
     kasarigan
    -0.61
     дописавши
    -0.60
    UnsafeEnabled
    -0.57
     للاسماء
    -0.55
    IsMutable
    -0.54
    UnknownFieldSet
    -0.54
     mergeFrom
    -0.52
     Administrativna
    -0.51
     invokingState
    -0.48
    POSITIVE LOGITS
     considérons
    0.44
    cdnjs
    0.44
    BASEPATH
    0.42
    Lo
    0.41
     Lo
    0.41
    Xna
    0.40
    mphony
    0.40
     gamb
    0.38
    SuspendLayout
    0.38
    multirow
    0.37
    Activations Density 0.119%

    No Known Activations