© 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. 9-GEMMASCOPE-RES-16K
    11. 10430
    Prev
    Next
    INDEX
    Explanations

    locations and references to geographic or civic structures

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

    Prepositions like "in", "on", "at"

    np_acts-logits-general · gemini-2.0-flash

    locations, buildings, and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    ,
    -0.35
    ion
    -0.34
     sus
    -0.34
     hå
    -0.33
    leistung
    -0.33
     mondo
    -0.32
    gewin
    -0.32
     curvas
    -0.32
     inesperado
    -0.31
     ideally
    -0.31
    POSITIVE LOGITS
    CloseOperation
    0.79
    modelBuilder
    0.72
     $_"
    0.64
    NUMX
    0.64
     AssemblyCompany
    0.62
     $_(
    0.62
    httphttps
    0.62
     Campus
    0.62
    fromnode
    0.62
     فريبيس
    0.61
    Activations Density 0.415%

    No Known Activations