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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 654
    Prev
    Next
    INDEX
    Explanations

    variable declarations and their formatting in code

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

    formatted output related to string representation and concatenation in programming

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

    structured data separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )");
    
    -0.75
    ."));
    -0.73
    ]";
    -0.71
    .",
    
    -0.68
    %");
    -0.67
    !")
    
    -0.67
    $")
    -0.67
    .")
    
    -0.67
    ?")
    -0.66
    .";
    
    -0.66
    POSITIVE LOGITS
    Geplaatst
    0.65
     محفوظة
    0.61
    ⓘ
    0.57
    Билгалдахарш
    0.55
     مرئيه
    0.54
     nahilalakip
    0.53
    !*\
    0.52
    stris
    0.52
    Lv
    0.52
    AddHtmlAttribute
    0.51
    Activations Density 0.064%

    No Known Activations