© 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. 5908
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or probability

    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
    ValueGenerated
    -0.56
    کلی
    -0.52
     Paglinawan
    -0.49
     daglig
    -0.48
    UPO
    -0.48
     chrétienne
    -0.46
     specchio
    -0.45
     attiva
    -0.45
     PMID
    -0.45
     rivol
    -0.44
    POSITIVE LOGITS
    Possibly
    1.63
    perhaps
    1.62
    maybe
    1.60
     Possibly
    1.59
     Perhaps
    1.59
     perhaps
    1.58
    Perhaps
    1.55
    Maybe
    1.52
    possibly
    1.51
    Vielleicht
    1.50
    Activations Density 0.260%

    No Known Activations