© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 37700
    Prev
    Next
    INDEX
    Explanations

    instances of the word "local" and related terms that emphasize locality or community engagement

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

    local and subsequent specific terms

    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
     declarat
    -0.32
    couvrez
    -0.31
     "
    -0.28
    śl
    -0.27
     Popov
    -0.27
    zysta
    -0.26
     kaik
    -0.26
    sprozess
    -0.25
    "])
    -0.24
     Stra
    -0.24
    POSITIVE LOGITS
     local
    1.54
    local
    1.43
    Local
    1.36
     lokale
    1.34
     locally
    1.34
     Local
    1.34
     LOCAL
    1.34
     lokal
    1.30
     lokalen
    1.28
    LOCAL
    1.24
    Activations Density 0.021%

    No Known Activations