© 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. 25-GEMMASCOPE-RES-16K
    6. 12780
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly related to calculations or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inevit
    -0.58
    füh
    -0.57
     Dummies
    -0.52
    ربای
    -0.51
    rug
    -0.49
    riculares
    -0.48
     specially
    -0.48
    efeated
    -0.48
     McLaugh
    -0.48
     fortunately
    -0.47
    POSITIVE LOGITS
    "));
    
    2.07
    '));
    
    1.90
    ")]
    
    1.89
    ");
    
    1.87
    '];
    
    1.87
    "];
    
    1.86
    ');
    
    1.85
    ));
    
    1.84
    ']);
    
    1.82
    ")));
    
    1.82
    Activations Density 4.607%

    No Known Activations