© 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. 18-GEMMASCOPE-RES-16K
    11. 8254
    Prev
    Next
    INDEX
    Explanations

    formal announcements regarding company-related developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following announcements/news

    np_acts-logits-general · gemini-2.0-flash

    announcements of new plans or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.86
     AssemblyProduct
    -0.78
    uttavia
    -0.72
     HasFactory
    -0.72
     autorytatywna
    -0.71
    __":
    -0.70
     ―――――
    -0.69
     plufieurs
    -0.68
    Posté
    -0.66
     समीक्षाओं
    -0.65
    POSITIVE LOGITS
    新たに
    0.65
     officially
    0.61
     new
    0.57
     offiziell
    0.56
     oficialmente
    0.56
     plans
    0.54
     latest
    0.54
    新的
    0.53
     resmi
    0.52
     finally
    0.51
    Activations Density 0.201%

    No Known Activations