© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6341
    Prev
    Next
    INDEX
    Explanations

    references to physical structures and architectural elements

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

    spatial and location-related terms, particularly related to height, floors, and positioning.

    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
    tanleria
    -0.65
     Réponses
    -0.40
     vált
    -0.38
    tierrez
    -0.37
    äure
    -0.36
    HCl
    -0.35
    kuuta
    -0.34
     stampa
    -0.33
    ljiv
    -0.33
    arnya
    -0.33
    POSITIVE LOGITS
     aloft
    0.85
     roof
    0.83
     above
    0.82
     maxHeight
    0.81
     sky
    0.81
     heights
    0.80
     Above
    0.76
    maxHeight
    0.76
     roofs
    0.75
     rooftop
    0.74
    Activations Density 0.320%

    No Known Activations