© 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. 8347
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to age, time periods, and measurements

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

    Numbers followed by a unit of measurement

    np_acts-logits-general · gemini-2.0-flash

    quantities and units

    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
     Anſ
    -0.76
    WebElementEntity
    -0.73
     myſelf
    -0.73
     itſelf
    -0.71
     ſay
    -0.70
     فريبيس
    -0.70
     Majefty
    -0.68
     Ukra
    -0.68
     InputDecoration
    -0.68
    出版年
    -0.67
    POSITIVE LOGITS
     می‌باشد
    0.76
    非常的
    0.60
     diatas
    0.58
      
    0.55
     evidences
    0.55
     таки
    0.54
     собою
    0.53
    出来た
    0.53
     whereas
    0.52
     (
    0.52
    Activations Density 0.224%

    No Known Activations