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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 2962
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing the absence of universal solutions or definitions in specific contexts

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

    specificity or lack thereof

    np_acts-logits-general · gemini-2.0-flash

    no specific definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.67
    AndEndTag
    -0.66
    ThroughAttribute
    -0.62
    новниш
    -0.58
     المعيارى
    -0.57
     nahilalakip
    -0.55
    "]);
    
    -0.55
     AssemblyProduct
    -0.54
     cherchés
    -0.54
     }}"></
    -0.54
    POSITIVE LOGITS
     definite
    0.76
     specific
    0.74
     Specific
    0.69
     preferred
    0.66
     مشخص
    0.65
     específico
    0.65
     defin
    0.63
    Specific
    0.63
     okreś
    0.61
    specific
    0.61
    Activations Density 0.315%

    No Known Activations