© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 21030
    Prev
    Next
    INDEX
    Explanations

    specific phrases and terms relevant to website management and configuration

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

    website or site

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     打印
    -0.45
     rutin
    -0.43
     Ahnung
    -0.42
    TableId
    -0.41
    圳
    -0.41
    :✨
    -0.41
     Signalez
    -0.40
    ItemName
    -0.39
     Gewähr
    -0.39
    inSlope
    -0.39
    POSITIVE LOGITS
     website
    1.09
     websites
    0.91
    website
    0.81
     portal
    0.77
     site
    0.76
     Website
    0.74
     web
    0.73
    网站
    0.70
     webbplats
    0.69
    網站
    0.66
    Activations Density 0.026%

    No Known Activations