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. 7174
    Prev
    Next
    INDEX
    Explanations

    quantitative information or numerical values related to instructions or processes

    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
    "]);
    
    -0.73
    ViewFeatures
    -0.72
    Spoljašnje
    -0.59
    AutoField
    -0.57
    "];
    
    -0.56
     precisione
    -0.55
     समीक्षक
    -0.53
    ']);
    
    -0.52
     élas
    -0.51
     progettazione
    -0.50
    POSITIVE LOGITS
     CURIAM
    0.75
    UnusedPrivate
    0.60
    writeFieldEnd
    0.59
     Puntos
    0.57
     bound
    0.56
    ValueStyle
    0.55
    PRNewswire
    0.55
    曖昧さ回避
    0.55
     estimés
    0.54
    jeev
    0.54
    Activations Density 0.154%

    No Known Activations