© 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. 67933
    Prev
    Next
    INDEX
    Explanations

    processes related to medical and biological mechanisms

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

    construction and mechanism

    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
    streams
    -0.42
    Tembelea
    -0.41
    awtextra
    -0.40
    ьаж
    -0.40
    EnableWeb
    -0.39
    ucap
    -0.39
    sac
    -0.39
     Middleton
    -0.39
    scales
    -0.38
    पया
    -0.38
    POSITIVE LOGITS
     فريبيس
    0.71
     typelib
    0.60
     الرياضيه
    0.52
    InputBorder
    0.47
    ClCompile
    0.44
    complexContent
    0.42
     awakeFromNib
    0.40
    뀔
    0.40
    VertexAttrib
    0.40
    舺
    0.39
    Activations Density 0.107%

    No Known Activations