© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84357
    Prev
    Next
    INDEX
    Explanations

    key terms and metrics related to authorship, medical data, virology, genes, traditional uses of bioactive components, safety ratings, social media interactions, actionable items, and contextual information

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

    technical metadata

    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
     secteur
    -0.40
    AddTagHelper
    -0.40
    chakra
    -0.39
    bootstrapcdn
    -0.38
     dam
    -0.38
     dyna
    -0.38
    ".$_
    -0.38
     Gem
    -0.37
     Kons
    -0.36
    gées
    -0.36
    POSITIVE LOGITS
    inSlope
    0.62
    хьтан
    0.58
    évaluateur
    0.57
    IVEREF
    0.55
     mergeFrom
    0.54
    oa̍t
    0.54
     հղումներ
    0.51
    SharedDtor
    0.50
     OMITBAD
    0.50
     jadx
    0.50
    Activations Density 0.130%

    No Known Activations