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. 9-GEMMASCOPE-RES-16K
    6. 9211
    Prev
    Next
    INDEX
    Explanations

    function calls and method declarations in programming language syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]?.
    -0.82
    ]--;
    -0.81
    ValueStyle
    -0.75
    ]));
    
    -0.72
     }}$}
    -0.72
     ]
    
    -0.71
    '],
    
    -0.71
    .');
    -0.70
     ſtand
    -0.69
    "],
    
    -0.68
    POSITIVE LOGITS
    initWithFrame
    0.49
     bolsillo
    0.48
    findpost
    0.47
     AssemblyCulture
    0.47
    NASDAQ
    0.46
     ComVisible
    0.45
     elétrica
    0.45
     idéia
    0.45
     nuvem
    0.45
     gră
    0.44
    Activations Density 0.780%

    No Known Activations