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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 2053
    Prev
    Next
    INDEX
    Explanations

    quotation marks and string delimiters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ‘
    -0.68
    -0.61
    >';
    
    -0.58
    -
    -0.51
    {?>
    -0.50
    ;
    -0.49
    ActivityResult
    -0.48
    {//
    -0.48
    ,
    -0.47
    $$\
    -0.47
    POSITIVE LOGITS
    %"
    0.94
    .'"
    0.79
    |"
    0.77
     Италијани
    0.76
    '"
    0.74
    parsedMessage
    0.73
    ViewFeatures
    0.71
    Geplaatst
    0.70
    ">"
    0.69
    %",
    0.69
    Activations Density 0.180%

    No Known Activations