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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 1411
    Prev
    Next
    INDEX
    Explanations

    conditional statements and control flow keywords in programming code

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

    Code branching: "else" keyword

    np_acts-logits-general · gemini-2.0-flash

    control flow blocks (else, default)

    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
    "));
    
    -1.51
    "):
    
    -1.50
    "];
    
    -1.48
    '));
    
    -1.44
    ']);
    
    -1.44
    .");
    
    -1.43
    ');
    
    -1.43
    ");
    
    -1.41
     "");
    
    -1.40
    )];
    
    -1.39
    POSITIVE LOGITS
    archiviato
    0.73
     للمعارف
    0.68
    Coordonnées
    0.67
    ervlak
    0.66
     quelconque
    0.66
     Commencez
    0.66
     дописавши
    0.64
    úgó
    0.63
    Vidite
    0.62
    angliski
    0.61
    Activations Density 0.067%

    No Known Activations