© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5916
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and territorial control

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

    geographic locations and regions, particularly in historical contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Bahn
    -0.39
    industan
    -0.37
    eradish
    -0.37
     народ
    -0.36
     homotopy
    -0.34
    verwijspagina
    -0.34
    slash
    -0.34
     arom
    -0.34
    一位
    -0.34
     intval
    -0.34
    POSITIVE LOGITS
    Chham
    0.63
     areas
    0.55
    ChildScrollView
    0.54
     neighbouring
    0.54
     South
    0.51
     southern
    0.50
     North
    0.50
     Bereiche
    0.50
     nearby
    0.50
     neighboring
    0.47
    Activations Density 0.564%

    No Known Activations