© 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. 10783
    Prev
    Next
    INDEX
    Explanations

    historical events and notable dates

    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
    ########.
    -0.63
    исленность
    -0.62
     العنوان
    -0.59
    ChildScrollView
    -0.59
    IsMutable
    -0.58
    Bronnen
    -0.57
     незавершена
    -0.57
    fromCharCode
    -0.57
    новништво
    -0.57
    eschön
    -0.56
    POSITIVE LOGITS
     élevées
    0.55
    guten
    0.55
    ktm
    0.54
    izh
    0.52
     maschile
    0.51
    canto
    0.51
    Reconnect
    0.50
    homonymie
    0.49
    хьтан
    0.49
    adpleegd
    0.48
    Activations Density 0.100%

    No Known Activations