© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 636
    Prev
    Next
    INDEX
    Explanations

    information related to specific events, such as timelines and historical occurrences

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

    Preceding "History" or following a number

    np_acts-logits-general · gemini-2.0-flash

    biography, life, history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.71
    Попис
    -0.70
    хьтан
    -0.68
     فريبيس
    -0.63
     Meksiku
    -0.62
    RectangleBorder
    -0.61
     betweenstory
    -0.60
     CanadaChoose
    -0.57
     defaultstate
    -0.57
    RTLR
    -0.56
    POSITIVE LOGITS
     feroit
    0.38
     infancia
    0.37
     Notable
    0.36
    存于互联网档案馆
    0.35
     desmotivaciones
    0.35
     débat
    0.34
     notable
    0.33
     impresiones
    0.33
     recueil
    0.33
     محفوظة
    0.33
    Activations Density 0.344%

    No Known Activations