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. 22-GEMMASCOPE-RES-16K
    6. 5965
    Prev
    Next
    INDEX
    Explanations

    programming symbols and operators commonly used in mathematical expressions or calculations

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

    Code snippets with parentheses and multiplication

    np_acts-logits-general · gemini-2.0-flash

    parentheses and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     none
    -0.79
     <<<<<<<<<<<<<<
    -0.72
     ''
    
    -0.59
     saites
    -0.59
     ""
    
    -0.59
     ")");
    -0.58
     الحره
    -0.57
     CGSize
    -0.55
     "")
    
    -0.55
     للاسماء
    -0.55
    POSITIVE LOGITS
     ((
    0.84
    ((
    0.75
     ("
    0.69
     (-
    0.68
    lamide
    0.65
    (-
    0.64
     (
    0.64
    mappedBy
    0.63
     (“
    0.63
     (((
    0.62
    Activations Density 0.537%

    No Known Activations