© 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. 31-GEMMASCOPE-RES-131K
    11. 15154
    Prev
    Next
    INDEX
    Explanations

    the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wikkeld
    -0.39
    iedad
    -0.38
     År
    -0.33
    öbb
    -0.31
     Weiter
    -0.31
    hasNext
    -0.31
    queado
    -0.31
    IsPostBack
    -0.31
     îns
    -0.30
     Akad
    -0.30
    POSITIVE LOGITS
    BufferException
    0.70
     EconPapers
    0.67
     kasarigan
    0.67
    IsContent
    0.65
     migrations
    0.56
    kháu
    0.56
     rollback
    0.54
    MigrationBuilder
    0.53
     migration
    0.53
     reverse
    0.52
    Activations Density 0.000%

    No Known Activations