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. 0-GEMMASCOPE-RES-16K
    6. 3366
    Prev
    Next
    INDEX
    Explanations

    ambiguous or unclear punctuation and whitespace usage in legal text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.86
    .
    -1.85
    ,
    -1.83
     (
    -1.56
    -
    -1.55
    '
    -1.51
     -
    -1.47
     "
    -1.44
     and
    -1.43
    /
    -1.43
    POSITIVE LOGITS
    )");
    
    3.88
    ")));
    
    3.87
    "]);
    
    3.84
    "])
    
    3.83
    '));
    
    3.81
    ?
    
    3.77
    )";
    
    3.75
    ".
    
    3.67
    "):
    
    3.64
    ']);
    
    3.63
    Activations Density 0.228%

    No Known Activations