© 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. 11623
    Prev
    Next
    INDEX
    Explanations

    references to pilot studies and related concepts in research

    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
    cassandra
    -0.59
     ang
    -0.53
    ख्या
    -0.52
     ràng
    -0.52
     νό
    -0.52
     ResponseEntity
    -0.51
    NINGS
    -0.51
     paz
    -0.51
     sa
    -0.50
    stanze
    -0.49
    POSITIVE LOGITS
     pilot
    3.65
     Pilot
    3.52
    pilot
    3.43
    Pilot
    3.37
     PILOT
    3.21
     pilots
    3.19
     Pilots
    3.02
     piloto
    2.63
     pilo
    2.58
     pilota
    2.56
    Activations Density 0.063%

    No Known Activations