© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1190
    Prev
    Next
    INDEX
    Explanations

    terms and classes related to dialog structures or user interface elements in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eeeeeeee
    -1.01
    ourite
    -0.93
     CME
    -0.91
    Cite
    -0.90
    e
    -0.89
    orme
    -0.89
     vene
    -0.89
     Sante
    -0.88
     Martine
    -0.87
    pile
    -0.87
    POSITIVE LOGITS
    ness
    1.26
    nya
    0.74
    n
    0.73
     архивлан
    0.70
    d
    0.70
    ([\
    0.68
    стоин
    0.67
    othed
    0.67
    ism
    0.67
     ISNI
    0.66
    Activations Density 1.025%

    No Known Activations