© 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 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. 20-GEMMASCOPE-RES-131K
    11. 103532
    Prev
    Next
    INDEX
    Explanations

    determinative articles or indicators of singularity in French and Spanish

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.92
    RTEE
    -0.71
    BeginContext
    -0.64
     Roskov
    -0.64
     فريبيس
    -0.60
    GTCX
    -0.59
    featureID
    -0.56
    WillAppear
    -0.55
    IVEREF
    -0.54
    Spoljašnje
    -0.53
    POSITIVE LOGITS
    ’
    0.41
    Occurrences
    0.38
    Diwedd
    0.38
    Optional
    0.38
    homonymie
    0.37
    ksesta
    0.36
    sendStatus
    0.35
    setDescription
    0.35
     Barbier
    0.35
    setMinimumSize
    0.35
    Activations Density 0.004%

    No Known Activations