© 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. 21-GEMMASCOPE-RES-16K
    11. 12324
    Prev
    Next
    INDEX
    Explanations

    references to the sequence or order of items, particularly in contexts such as book installments or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.72
    corsi
    -0.61
    ския
    -0.59
     determinadas
    -0.54
     fleste
    -0.53
    various
    -0.53
     Various
    -0.52
    各
    -0.52
    눠
    -0.51
     Parenthood
    -0.51
    POSITIVE LOGITS
     only
    1.15
     result
    1.03
     same
    1.01
     easiest
    0.87
     culmination
    0.87
     perfect
    0.82
     least
    0.82
    only
    0.81
     first
    0.80
     ONLY
    0.80
    Activations Density 0.318%

    No Known Activations