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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 9283
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the "for" loop keyword in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.89
    )");
    
    -0.86
    ]='\
    -0.86
    >",
    
    -0.84
    ".
    
    -0.79
    ")));
    
    -0.79
    ]."
    -0.79
     }}"></
    -0.78
     resourceCulture
    -0.77
    ::~
    -0.77
    POSITIVE LOGITS
    for
    1.35
     for
    0.90
     For
    0.83
    FOR
    0.82
    if
    0.78
     FOR
    0.76
    while
    0.72
    For
    0.72
    foreach
    0.72
    fore
    0.58
    Activations Density 0.271%

    No Known Activations