© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12667
    Prev
    Next
    INDEX
    Explanations

    technical terms related to projectiles and their specifications

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

    Degrees, angles, or measurements

    np_acts-logits-general · gemini-2.0-flash

    degree, delay, engages, and

    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
     fubject
    -0.60
     pleaſure
    -0.56
     ſtate
    -0.54
     purpoſe
    -0.52
     viſ
    -0.50
     ſeveral
    -0.49
     ſche
    -0.47
     ftate
    -0.47
     tranſ
    -0.46
    fastjson
    -0.46
    POSITIVE LOGITS
    tanleria
    0.52
     Chwiliwch
    0.49
     кӀ
    0.47
     robar
    0.47
    +#+#
    0.45
     الرياضيه
    0.45
    ContentAlignment
    0.44
    ubov
    0.44
    áky
    0.44
     optimised
    0.43
    Activations Density 0.533%

    No Known Activations