© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 100776
    Prev
    Next
    INDEX
    Explanations

    mentions of "notable" people or entities

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

    notable people and contributions

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Machine
    -0.47
     HasFactory
    -0.47
     Mesin
    -0.47
     İş
    -0.46
     automatico
    -0.46
    machine
    -0.45
    جغرافيا
    -0.43
     ocz
    -0.43
    Mechan
    -0.43
     aeroplane
    -0.42
    POSITIVE LOGITS
     Notable
    1.17
     notable
    1.16
    Notable
    1.12
     noteworthy
    1.06
     notables
    0.90
     noticeable
    0.82
     noted
    0.82
     bemerk
    0.79
     remarkable
    0.79
    noted
    0.77
    Activations Density 0.008%

    No Known Activations