© 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. 128614
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate realizations or insights

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

    personal realizations

    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
    เย
    -0.27
    ího
    -0.27
     nomme
    -0.27
    gulier
    -0.26
    规定
    -0.26
    couleur
    -0.26
    yev
    -0.25
     évêque
    -0.24
     royaume
    -0.24
     free
    -0.24
    POSITIVE LOGITS
    InSection
    0.70
    OCCURRED
    0.68
    yntaxException
    0.65
     dawned
    0.65
    Autoritní
    0.65
    URLException
    0.65
    featureID
    0.64
    şört
    0.64
    MemoryWarning
    0.63
     GenerationType
    0.63
    Activations Density 0.016%

    No Known Activations