Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 6070
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables associated with inequalities and limits

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

    Mathematical symbols or expressions

    np_acts-logits-general · gemini-2.0-flash

    closing and opening braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )))));
    -0.71
    )]);
    -0.64
     EconPapers
    -0.63
    ])));
    -0.62
    });*/
    -0.58
    ']);
    
    -0.57
    //});
    -0.55
    )\}$
    -0.55
     */;
    -0.55
    ]]
    
    -0.54
    POSITIVE LOGITS
    }{
    1.71
    }{\
    1.23
     }{
    1.18
    }}{
    1.04
    )}{
    1.04
    "){
    1.00
    </strong>
    0.95
    }{(
    0.94
    ){
    0.89
    }{-
    0.88
    Activations Density 0.339%

    No Known Activations