© 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. 637
    Prev
    Next
    INDEX
    Explanations

    expressions related to distance or spatial separation

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

    spatial descriptions involving distance and measurement.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    descriptions of physical distance or remote locations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    фраструк
    -0.28
    upon
    -0.27
     erw
    -0.27
     caráter
    -0.26
     osob
    -0.25
    仔
    -0.25
     ugy
    -0.24
     Ambiental
    -0.24
     tried
    -0.24
     заключа
    -0.24
    POSITIVE LOGITS
     distant
    1.05
     lontano
    0.99
    遠
    0.95
     distance
    0.94
     remote
    0.94
    distant
    0.93
     Distant
    0.92
     jauh
    0.90
     distances
    0.90
     farthest
    0.88
    Activations Density 0.301%

    No Known Activations