Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12702
    Prev
    Next
    INDEX
    Explanations

    location and directional information in a context of navigation or description of places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.67
     autorytatywna
    -0.55
    StructEnd
    -0.47
    RenderAtEndOf
    -0.47
    choon
    -0.46
    httphttps
    -0.41
     persoonlijke
    -0.40
     Gelegenheit
    -0.40
    tableFuture
    -0.40
     möjligt
    -0.40
    POSITIVE LOGITS
    webElementXpaths
    0.49
    contentLoaded
    0.43
     Zwer
    0.42
     CLOSED
    0.39
    fclose
    0.38
     directions
    0.38
     ears
    0.38
    FromDB
    0.38
     ver
    0.37
    InjectAttribute
    0.37
    Activations Density 0.138%

    No Known Activations