© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7786
    Prev
    Next
    INDEX
    Explanations

    references to "Kan" and its related terms, as well as mentions of "canonical" transformations

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

    the word "Kan" (likely part of proper nouns or geographic references like "Kansas" or "Kanagawa").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ValueStyle
    -0.45
    tanleria
    -0.41
    jsxFileName
    -0.40
    elemField
    -0.39
     Paglinawan
    -0.37
    featureID
    -0.36
     Belle
    -0.35
    verti
    -0.35
     Tod
    -0.34
     kunna
    -0.34
    POSITIVE LOGITS
    CAN
    0.65
    Can
    0.59
    IsMutable
    0.58
    CANT
    0.58
    Kan
    0.56
    Cant
    0.55
     Cana
    0.54
     Candace
    0.53
    下载附件
    0.53
     Can
    0.53
    Activations Density 0.270%

    No Known Activations