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. 11-GEMMASCOPE-RES-16K
    6. 13261
    Prev
    Next
    INDEX
    Explanations

    references to grants and their applications or statuses

    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
    kamer
    -0.80
     sjø
    -0.72
    dziew
    -0.72
     réve
    -0.70
    İY
    -0.70
     Hig
    -0.70
     Buenos
    -0.69
     Argy
    -0.69
    ```
    -0.69
    Buenos
    -0.69
    POSITIVE LOGITS
     Grant
    1.66
     Grants
    1.58
     GRANT
    1.56
     grant
    1.53
     grants
    1.52
    Grants
    1.48
    Grant
    1.48
    GRANT
    1.38
    grants
    1.35
    grant
    1.34
    Activations Density 0.105%

    No Known Activations