© 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. 13590
    Prev
    Next
    INDEX
    Explanations

    specific programming and technical terms related to object manipulation and data processing

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

    Follows words suggesting necessity or requirement

    np_acts-logits-general · gemini-2.0-flash

    shows or needs

    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
     formal
    -0.31
     ter
    -0.30
    setAuto
    -0.30
     et
    -0.28
     auto
    -0.28
     past
    -0.28
     geçti
    -0.27
     gam
    -0.26
     al
    -0.26
    viewport
    -0.26
    POSITIVE LOGITS
    UnusedPrivate
    0.88
     متعلقه
    0.86
     ujednoznacz
    0.78
    findpost
    0.77
     ब्रेकडाउन
    0.76
    RenderAtEndOf
    0.74
    ReusableCell
    0.74
    InjectAttribute
    0.73
    LabelTagHelper
    0.71
    RTLR
    0.71
    Activations Density 1.274%

    No Known Activations