© 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
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 715
    Prev
    Next
    INDEX
    Explanations

    sections and organization within academic papers

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

    overview sections and introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.62
     propOrder
    -0.60
    adaptiveStyles
    -0.59
    tagHelperRunner
    -0.59
     EconPapers
    -0.59
     ModelExpression
    -0.59
     CanadaChoose
    -0.55
    الإنجليزية
    -0.54
    errHandler
    -0.54
    mybatisplus
    -0.52
    POSITIVE LOGITS
     introductory
    0.63
     explaining
    0.56
     wyja
    0.55
     explicou
    0.54
     explanatory
    0.54
     background
    0.52
     Erklärung
    0.51
     explain
    0.50
     clarifying
    0.50
     educate
    0.49
    Activations Density 0.107%

    No Known Activations