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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4450
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory compliance and procedural evaluations

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

    regulations or legal procedures

    np_acts-logits-general · gemini-2.0-flash

    proposed rule finalization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     незавершена
    -0.86
    ValueStyle
    -0.75
    printStackTrace
    -0.70
    ImageContext
    -0.63
     personlig
    -0.60
    LLocation
    -0.59
    lencia
    -0.58
     consciousness
    -0.56
    
    -0.56
     खरीदा
    -0.53
    POSITIVE LOGITS
     rule
    0.96
     draft
    0.74
    rule
    0.73
     Rule
    0.71
     comment
    0.70
     final
    0.70
     proposed
    0.70
     rules
    0.69
     Adop
    0.67
     promulg
    0.67
    Activations Density 0.674%

    No Known Activations