© 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. 628
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and function calls

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

    handler, handle, api, render

    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
    TagMode
    -0.40
    hor
    -0.32
    endl
    -0.28
     Either
    -0.28
     hor
    -0.28
     Man
    -0.28
    fahren
    -0.27
    kään
    -0.27
    Either
    -0.26
     Eastern
    -0.26
    POSITIVE LOGITS
     مشين
    0.85
     AssemblyCompany
    0.73
    出版年
    0.68
     AttributeSet
    0.66
    
    0.64
    脚注の使い方
    0.61
    Tikang
    0.59
    yntaxException
    0.59
     imagui
    0.59
    <unused21>
    0.58
    Activations Density 0.043%

    No Known Activations