© 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. 12318
    Prev
    Next
    INDEX
    Explanations

    expressions of hesitation or uncertainty

    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
    而非
    -0.62
    AutoField
    -0.60
    而不是
    -0.56
     both
    -0.44
    COUVER
    -0.44
     directly
    -0.44
    eX
    -0.43
    OuterClass
    -0.42
     idk
    -0.41
    RuntimeObject
    -0.41
    POSITIVE LOGITS
     tampoco
    1.16
     nor
    1.16
     either
    1.02
     anymore
    0.97
    either
    0.89
    Tikang
    0.88
     sondern
    0.88
     Tampoco
    0.88
     Theſe
    0.83
    Nor
    0.83
    Activations Density 0.256%

    No Known Activations