© 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. 11-GEMMASCOPE-RES-16K
    11. 13557
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory approvals and medical products

    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
    Begriffsklä
    -0.52
    JsonFormat
    -0.49
     ECONOMY
    -0.47
    ExecuteReader
    -0.47
    printStackTrace
    -0.46
    baus
    -0.45
    aş
    -0.45
    IndentedString
    -0.43
    TagHelper
    -0.43
    ázs
    -0.43
    POSITIVE LOGITS
     Efq
    0.76
    cristo
    0.66
     perfons
    0.62
     Majefty
    0.62
     himſelf
    0.61
    GEBURTSDATUM
    0.61
    UnknownFieldSet
    0.61
     invokingState
    0.61
    بوابة
    0.60
     uſed
    0.59
    Activations Density 0.488%

    No Known Activations