© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 99126
    Prev
    Next
    INDEX
    Explanations

    occurrences of accented 'é' characters

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

    é character in scientific contexts

    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
     يتيمه
    -0.65
    böz
    -0.60
     ainfi
    -0.60
    intéress
    -0.56
     desmotivaciones
    -0.55
    ésult
    -0.54
    StructEnd
    -0.52
     trône
    -0.50
    benhavn
    -0.50
    ntown
    -0.49
    POSITIVE LOGITS
    é
    1.93
    É
    1.20
    eacute
    0.94
    té
    0.91
    cé
    0.90
    lé
    0.86
    dé
    0.84
    ié
    0.84
     é
    0.81
    ré
    0.81
    Activations Density 0.008%

    No Known Activations