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. 24-GEMMASCOPE-RES-16K
    6. 16371
    Prev
    Next
    INDEX
    Explanations

    patterns related to programming code or technical specifications

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

    LaTeX code and special characters

    np_acts-logits-general · gemini-2.0-flash

    mathematical delimiters and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '));
    -0.65
    ']);
    -0.65
    AsUp
    -0.64
    ])));
    -0.61
     ]);
    -0.61
    ()]);
    -0.60
     "'");
    -0.58
    "]));
    -0.58
    '));
    
    -0.57
    ']);
    
    -0.57
    POSITIVE LOGITS
    }{|
    0.92
    enumi
    0.91
    enumii
    0.76
    }{
    0.75
     незавершена
    0.74
    LEncoder
    0.71
    |}{
    0.66
    NUMX
    0.63
    multirow
    0.63
    }{$\
    0.62
    Activations Density 0.019%

    No Known Activations