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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1120
    Prev
    Next
    INDEX
    Explanations

    function calls and method invocations within code

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

    method chaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    <bos>
    -0.80
    parsedMessage
    -0.73
     Мексичка
    -0.66
    各样的
    -0.65
    typeorm
    -0.65
    tagHelperRunner
    -0.61
     mijne
    -0.61
     Infórmanos
    -0.58
     }}$}
    -0.58
    ecake
    -0.57
    POSITIVE LOGITS
    ().
    0.87
    ❤️❤️
    0.63
    ()->
    0.56
    ().__
    0.55
    >().
    0.50
    ()?.
    0.49
     ().
    0.49
     Srl
    0.49
     apparently
    0.48
    																			
    0.47
    Activations Density 0.007%

    No Known Activations