Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 6092
    Prev
    Next
    INDEX
    Explanations

    statements related to legal or constitutional issues, particularly involving separation of church and state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     udaler
    -0.57
    nium
    -0.57
    mmings
    -0.55
    ριά
    -0.53
     AppCompatTheme
    -0.53
    bleshooting
    -0.52
    原文
    -0.52
    тельству
    -0.51
    λίου
    -0.51
    DockStyle
    -0.51
    POSITIVE LOGITS
     Inscrivez
    0.60
    actually
    0.59
    Composable
    0.58
    RegistryLite
    0.56
     fufficient
    0.54
    bueno
    0.53
     Efq
    0.52
     actually
    0.52
     */
    
    
    0.52
     Архів
    0.52
    Activations Density 0.291%

    No Known Activations