© 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. 20-GEMMASCOPE-RES-131K
    11. 106378
    Prev
    Next
    INDEX
    Explanations

    connections between subjects and their relationships or assessments in various contexts

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

    presumably, apparently, seems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.67
     كومونز
    -0.64
    majánló
    -0.62
    
    -0.61
    kháu
    -0.60
    expandindo
    -0.59
     HttpNotFound
    -0.59
     fieldNum
    -0.59
     OMITBAD
    -0.59
    ésultats
    -0.58
    POSITIVE LOGITS
     semblent
    0.39
     semble
    0.39
    Somewhere
    0.36
    と思われる
    0.35
    mutlich
    0.35
     presumably
    0.34
    seems
    0.33
    少なくとも
    0.33
    hintText
    0.33
     somewhere
    0.32
    Activations Density 0.235%

    No Known Activations