© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11410
    Prev
    Next
    INDEX
    Explanations

    references to advanced techniques, technologies, or treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spitfire
    -0.76
    enumi
    -0.74
    SqlClient
    -0.73
    numerusform
    -0.73
    AsStream
    -0.73
     Wembley
    -0.71
     cricketer
    -0.68
     Cumbria
    -0.68
    wußt
    -0.67
     PKK
    -0.67
    POSITIVE LOGITS
     advanced
    3.47
    advanced
    3.26
     Advanced
    3.24
    Advanced
    3.12
     ADVANCED
    2.95
    ADVANCED
    2.68
     advance
    2.60
     Advance
    2.58
    Advance
    2.47
    vanced
    2.37
    Activations Density 0.044%

    No Known Activations