© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 65028
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and coordinates related to coastlines and offshore areas

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

    off the coast of

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     princí
    -0.45
     Suomessa
    -0.41
     dasarnya
    -0.40
     Monfieur
    -0.40
     světě
    -0.38
     itſelf
    -0.37
     Curitiba
    -0.37
     EconPapers
    -0.36
     CANADA
    -0.36
    erçe
    -0.36
    POSITIVE LOGITS
     near
    0.81
     Near
    0.79
    Near
    0.78
    near
    0.74
     NEAR
    0.63
     препратки
    0.61
    NEAR
    0.58
     off
    0.57
    Havolalar
    0.54
     nahe
    0.54
    Activations Density 0.059%

    No Known Activations