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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 14967
    Prev
    Next
    INDEX
    Explanations

    elements related to programming logic, counts, and data structures

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

    Code containing increment operators

    np_acts-logits-general · gemini-2.0-flash

    code incrementing variables

    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
    )");
    
    -0.97
    "):
    
    -0.90
    ).
    
    -0.88
    )";
    
    -0.85
    "){
    
    -0.84
    "));
    
    -0.83
    ")
    
    -0.83
    ),”
    -0.83
    '):
    
    -0.82
    }),
    
    -0.81
    POSITIVE LOGITS
    ++;
    0.66
    +#+#
    0.61
     +=
    0.54
    webElementGuid
    0.53
     InputDecoration
    0.49
    ctomy
    0.47
    bollah
    0.47
    భ
    0.47
     nahilalakip
    0.47
     =
    0.46
    Activations Density 0.037%

    No Known Activations