© 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. 671
    Prev
    Next
    INDEX
    Explanations

    references to the concept of value or assessment in various contexts

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

    reasons and concessions

    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
    UnusedPrivate
    -0.59
    UrlResolution
    -0.56
     ModelExpression
    -0.52
    webElementXpaths
    -0.49
    Климат
    -0.47
    كويكب
    -0.43
    AntiForgeryToken
    -0.43
    новништво
    -0.42
    Rujuakan
    -0.42
    ContentAsync
    -0.42
    POSITIVE LOGITS
     maybe
    0.47
    毕竟
    0.43
     Maybe
    0.42
    
    0.42
    Maybe
    0.40
     jedenfalls
    0.40
     mention
    0.40
     immerhin
    0.38
     erwähnt
    0.38
     quizá
    0.38
    Activations Density 0.066%

    No Known Activations