© 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. 14453
    Prev
    Next
    INDEX
    Explanations

    references to scientific measurements and medical conditions

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

    Immediately follows mathematical or code symbols

    np_acts-logits-general · gemini-2.0-flash

    information, choice, ratio, restriction, intra

    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
     المعيارى
    -0.84
    RectangleBorder
    -0.69
    contentLoaded
    -0.69
     resourceCulture
    -0.67
    CodedInputStream
    -0.65
    InputBorder
    -0.64
    libft
    -0.60
     estekak
    -0.57
    rungsseite
    -0.56
    ItemBackground
    -0.55
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.49
    AddTagHelper
    0.46
     certi
    0.44
    \{\\
    0.43
     mús
    0.41
    惠
    0.38
    pers
    0.38
     bl
    0.38
    imp
    0.36
    ZAR
    0.36
    Activations Density 1.384%

    No Known Activations