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. 761
    Prev
    Next
    INDEX
    Explanations

    topics and discussions related to advancements in technology and education

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

    technology and tools

    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
    setVerticalGroup
    -0.42
     larmes
    -0.40
    ública
    -0.39
     destinée
    -0.38
     circonst
    -0.38
     ruedas
    -0.37
    UserDetails
    -0.37
     provisoire
    -0.36
     drapeau
    -0.36
     userDetails
    -0.36
    POSITIVE LOGITS
     technology
    0.85
     technologies
    0.79
     technological
    0.71
     automation
    0.69
     للاسماء
    0.67
    technology
    0.66
     innovations
    0.66
     technologie
    0.65
     Technology
    0.63
     teknologi
    0.63
    Activations Density 0.048%

    No Known Activations