© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 578
    Prev
    Next
    INDEX
    Explanations

    references to culinary experiences and notes on overlooked cultural contributions

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

    Under-appreciated or unknown things

    np_acts-logits-general · gemini-2.0-flash

    obscure, forgotten, or overlooked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    ViewFeatures
    -0.45
     الميل
    -0.44
    蚪
    -0.41
    AddHtmlAttribute
    -0.40
    findpost
    -0.35
     Loose
    -0.35
    cord
    -0.35
    #+#
    -0.33
     Lokales
    -0.32
    зулта
    -0.32
    POSITIVE LOGITS
     obscure
    0.65
    forgotten
    0.63
     obscurity
    0.60
    地味
    0.56
     forgotten
    0.56
     underrated
    0.52
    Fordítás
    0.52
     lesser
    0.52
     overlooked
    0.51
    sidemargin
    0.50
    Activations Density 0.434%

    No Known Activations