© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2688
    Prev
    Next
    INDEX
    Explanations

    corporate or organizational entities and their associated details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %")
    -0.88
    '):
    
    -0.87
    ")));
    
    -0.85
    ?");
    -0.82
    "):
    
    -0.81
    ))));
    -0.78
     }}$}
    -0.78
    */;
    -0.77
    ?")
    -0.77
    )";
    
    -0.76
    POSITIVE LOGITS
     المتحدة
    0.57
    .,
    0.53
     Rossetti
    0.48
    万美元
    0.48
    rimidine
    0.48
    亿美元
    0.47
    updateOne
    0.47
    InputElement
    0.46
    FormTagHelper
    0.46
    ohjel
    0.46
    Activations Density 0.734%

    No Known Activations