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. 20-GEMMASCOPE-RES-16K
    6. 2196
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and attributes related to individuals or items, such as names and descriptions

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

    Followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    San Luis Obispo County

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}$}
    -0.80
    '},
    
    -0.74
    makeText
    -0.73
    rawDesc
    -0.73
    =");
    -0.71
    "},
    
    -0.71
    >",
    
    -0.70
    :");
    
    -0.69
    }")
    
    -0.69
    )";
    
    -0.69
    POSITIVE LOGITS
     (,
    0.58
     ·
    0.55
     урна
    0.52
     ,.
    0.49
     preuves
    0.48
     sebagainya
    0.48
    ItemGroup
    0.46
     ()
    0.46
     ⋅
    0.46
     undefined
    0.45
    Activations Density 0.477%

    No Known Activations