© 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. 12122
    Prev
    Next
    INDEX
    Explanations

    prominent single words or short phrases that establish key ideas or themes within the text

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

    phrase

    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
     overall
    -0.41
     Overall
    -0.32
    overall
    -0.32
     formula
    -0.31
     bland
    -0.31
     rze
    -0.31
    Overall
    -0.30
     veo
    -0.29
    contentType
    -0.28
     Elba
    -0.28
    POSITIVE LOGITS
     excerpts
    0.80
     excerpt
    0.79
     extracts
    0.79
     Quoted
    0.72
    tagHelperRunner
    0.71
    extrait
    0.71
     quotes
    0.69
    AddTagHelper
    0.68
     Extracts
    0.68
    excerpt
    0.68
    Activations Density 0.001%

    No Known Activations