© 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. 3729
    Prev
    Next
    INDEX
    Explanations

    numerical data and values related to quantities, measurements, and costs

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

    Following "up to"

    np_acts-logits-general · gemini-2.0-flash

    up to a maximum amount

    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
    rxjs
    -0.45
    FieldOffsetTable
    -0.38
    niejs
    -0.36
    anneer
    -0.35
    iddhar
    -0.34
     DELLE
    -0.33
    IANGLES
    -0.33
    FormTagHelper
    -0.32
     APPEALS
    -0.32
    強
    -0.31
    POSITIVE LOGITS
     maxLength
    0.68
    maxSize
    0.61
     maxWidth
    0.60
     ymax
    0.59
    Maximum
    0.59
    maximum
    0.59
     maxima
    0.57
     maximum
    0.57
     maxSize
    0.57
     maximal
    0.57
    Activations Density 0.327%

    No Known Activations