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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 38021
    Prev
    Next
    INDEX
    Explanations

    structured data elements or definitions within a document

    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
     IBOutlet
    -0.43
    HtmlAttribute
    -0.43
     samochod
    -0.34
     betreft
    -0.34
    oudoune
    -0.34
     widok
    -0.34
    wound
    -0.33
     ejus
    -0.33
     zná
    -0.33
     miłości
    -0.33
    POSITIVE LOGITS
    تقاوى
    0.58
    期刊论文
    0.57
    StoreMessageInfo
    0.51
     ***!
    0.50
     defaultstate
    0.48
    SourceChecksum
    0.47
    $_['
    0.47
    MLLoader
    0.45
    ViewFeatures
    0.42
     Chwiliwch
    0.39
    Activations Density 0.000%

    No Known Activations