© 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. 10331
    Prev
    Next
    INDEX
    Explanations

    references to geographical zones or regions

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

    "zone" (capitalized or lowercase)

    np_acts-logits-general · gemini-2.0-flash

    zone and zones

    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
     cheveux
    -0.38
     suivants
    -0.38
     néer
    -0.35
     définiti
    -0.35
     souten
    -0.35
     manquante
    -0.35
     Ejército
    -0.34
     Úl
    -0.34
     }}"></
    -0.34
     Fehl
    -0.33
    POSITIVE LOGITS
     zone
    2.52
     Zone
    2.44
    Zone
    2.36
     ZONE
    2.31
    zone
    2.30
     zones
    2.28
     Zones
    2.22
    ZONE
    2.17
    zones
    2.00
    Zones
    1.90
    Activations Density 0.212%

    No Known Activations