© 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. 602
    Prev
    Next
    INDEX
    Explanations

    specific entities or terms related to medical conditions or biological structures

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

    programming concepts and terms

    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
     ModelExpression
    -0.54
    msgTypes
    -0.52
    webElementXpaths
    -0.52
    Rüyada
    -0.48
     nahilalakip
    -0.47
     ModelRenderer
    -0.45
     merek
    -0.40
     CanadaChoose
    -0.40
    principalColumn
    -0.39
    GOTREF
    -0.39
    POSITIVE LOGITS
     للاسماء
    0.54
    хьтан
    0.48
     StatefulWidget
    0.47
     ExecuteAsync
    0.43
    OpenHelper
    0.40
     gate
    0.39
    gate
    0.38
     Chau
    0.38
     Gate
    0.37
     endwhile
    0.37
    Activations Density 0.015%

    No Known Activations