© 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. 5350
    Prev
    Next
    INDEX
    Explanations

    references to statistical or analytical concepts in the context of decision-making or agency

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

    punctuation and contrast words

    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
    Personensuche
    -0.49
     endwhile
    -0.35
    MemoryWarning
    -0.35
     dual
    -0.34
     Exactos
    -0.34
    ↻
    -0.33
    ）』
    -0.31
     χ
    -0.31
     optimal
    -0.31
    eace
    -0.30
    POSITIVE LOGITS
     propOrder
    0.63
    SharedDtor
    0.60
     Anſ
    0.54
     Reſ
    0.53
     يتيمه
    0.50
    StoryboardSegue
    0.49
    DECREF
    0.47
    ISupport
    0.45
    avigation
    0.44
     desmotivaciones
    0.44
    Activations Density 0.190%

    No Known Activations