© 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. 1576
    Prev
    Next
    INDEX
    Explanations

    technical terminology and complex concepts related to scientific methodologies and materials

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

    Tokens before units of measure or equations

    np_acts-logits-general · gemini-2.0-flash

    AtPosition Wherever

    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
     nakalista
    -0.54
    ScopeManager
    -0.51
     estekak
    -0.50
     HttpNotFound
    -0.46
    ￡
    -0.41
    SHIRE
    -0.41
     beginnetje
    -0.41
    Filmographie
    -0.40
     становника
    -0.40
     SwitchCompat
    -0.39
    POSITIVE LOGITS
    DockStyle
    0.79
    AtPosition
    0.46
    MessageTagHelper
    0.44
     wherever
    0.43
    outside
    0.39
     Tại
    0.38
     Outside
    0.37
     outside
    0.36
     Wherever
    0.36
    InputBorder
    0.36
    Activations Density 1.255%

    No Known Activations