© 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. 23-GEMMASCOPE-RES-16K
    11. 9299
    Prev
    Next
    INDEX
    Explanations

    numeric representations or sequences related to time or measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.53
    驾
    -0.44
    Composable
    -0.43
    ParallelGroup
    -0.41
    к
    -0.41
    ↵↵
    -0.40
    www
    -0.40
     www
    -0.40
    чета
    -0.38
    Dru
    -0.37
    POSITIVE LOGITS
     Efq
    1.03
    BibitemShut
    0.95
     мәкал
    0.92
     myſelf
    0.90
     Monfieur
    0.90
     $_"
    0.85
     ſeveral
    0.83
     itſelf
    0.83
     himſelf
    0.81
    ^(@)
    0.81
    Activations Density 0.368%

    No Known Activations