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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13897
    Prev
    Next
    INDEX
    Explanations

    references to legal rules and regulations

    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
    et
    -0.65
    ing
    -0.55
    ↵↵
    -0.50
     half
    -0.48
     together
    -0.48
    ;
    -0.47
    ,
    -0.46
    i
    -0.45
     بها
    -0.45
    qui
    -0.45
    POSITIVE LOGITS
     Мексичка
    1.02
     للمعارف
    1.00
     Infórmanos
    1.00
    NUMX
    0.95
    AutoresizingMask
    0.92
    ReusableCell
    0.87
    +#+
    0.87
    ########.
    0.85
    rrggbb
    0.84
     estekak
    0.84
    Activations Density 0.382%

    No Known Activations