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. 17-GEMMASCOPE-RES-16K
    6. 6184
    Prev
    Next
    INDEX
    Explanations

    structured data and code syntax in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ་་
    -1.35
    
    -1.33
     ―――――
    -1.32
     propOrder
    -1.31
     saites
    -1.30
     للاسماء
    -1.29
     myſelf
    -1.28
    SharedDtor
    -1.27
    writeFieldEnd
    -1.27
     itſelf
    -1.27
    POSITIVE LOGITS
     
    0.98
    ↵
    0.83
     (
    0.82
    ↵↵
    0.82
    <eos>
    0.79
    ,
    0.79
     the
    0.78
    (
    0.76
    /
    0.73
     non
    0.71
    Activations Density 3.049%

    No Known Activations