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. 3254
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly at the end of sentences

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

    Code punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation and code blocks

    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
    And
    -0.88
     you
    -0.81
    I
    -0.80
     maybe
    -0.78
     I
    -0.75
    Maybe
    -0.73
     now
    -0.72
     what
    -0.70
     Maybe
    -0.69
    and
    -0.69
    POSITIVE LOGITS
    )");
    
    1.44
    )";
    
    1.36
    ]--;
    1.28
    ".
    
    1.22
    "):
    
    1.21
    ")));
    
    1.20
    ]";
    1.20
    '},
    
    1.18
    .";
    
    1.18
    $.
    
    1.17
    Activations Density 0.851%

    No Known Activations