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. 5-GEMMASCOPE-RES-16K
    6. 11247
    Prev
    Next
    INDEX
    Explanations

    the presence of numeric values and references to measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,:);
    -0.94
    )‏
    -0.85
    Vea
    -0.83
     ―――――
    -0.80
    ,:]
    -0.75
     Efq
    -0.71
    Personensuche
    -0.70
    )");
    
    -0.69
    ціє
    -0.69
     Versace
    -0.69
    POSITIVE LOGITS
    3
    1.26
    5
    1.05
    4
    1.02
     three
    0.99
    three
    0.96
    6
    0.95
     Three
    0.88
    0
    0.87
    THREE
    0.84
    2
    0.82
    Activations Density 0.603%

    No Known Activations