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. 9-GEMMASCOPE-RES-16K
    6. 15542
    Prev
    Next
    INDEX
    Explanations

    HTML and XML component attributes and selectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hdashline
    -0.69
    ']))
    
    -0.63
     ""],
    -0.61
     Jefus
    -0.58
    ViewHolder
    -0.56
    \"");
    -0.56
    sequelize
    -0.56
    ']
    
    -0.55
    знес
    -0.55
    Bronnen
    -0.54
    POSITIVE LOGITS
    CrossRef
    1.41
     crossorigin
    1.13
     @"/
    0.97
    AddTagHelper
    0.95
    DataAnnotations
    0.86
    ="@+
    0.85
     <<<<<<<<<<<<<<
    0.84
    </thead>
    0.77
    
    0.76
    PerformLayout
    0.73
    Activations Density 0.003%

    No Known Activations