© 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. 101124
    Prev
    Next
    INDEX
    Explanations

    assignment operators and method calls in code

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

    indices after i or j

    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
     proper
    -0.39
    uestamente
    -0.35
     generales
    -0.35
     remercier
    -0.34
     properly
    -0.34
     Serbie
    -0.34
     satisfying
    -0.33
     adequad
    -0.32
     Allgeme
    -0.32
     appropriately
    -0.32
    POSITIVE LOGITS
    afficheront
    0.88
    Personensuche
    0.85
     kasarigan
    0.79
    TypedDataSet
    0.75
    adaptiveStyles
    0.75
     صوتيه
    0.74
    expandindo
    0.73
    awtextra
    0.72
    fromnode
    0.71
    aarrggbb
    0.71
    Activations Density 0.004%

    No Known Activations