Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1108
    Prev
    Next
    INDEX
    Explanations

    numerical values and associated units of measurement

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

    numbers, quantities, and measurements

    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
     referrerpolicy
    -0.29
    ประ
    -0.28
    ;
    -0.28
    าะ
    -0.27
    ,
    -0.27
    .
    -0.26
    )}.
    -0.26
     conflicts
    -0.26
     annat
    -0.26
     Zustimmung
    -0.26
    POSITIVE LOGITS
    kháu
    0.80
    parsedMessage
    0.79
     Photocase
    0.75
     насељу
    0.73
     betweenstory
    0.72
    Obrázky
    0.71
    MemoryWarning
    0.71
     typelib
    0.69
    EndContext
    0.68
    setVerticalGroup
    0.66
    Activations Density 0.108%

    No Known Activations