© 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. 4095
    Prev
    Next
    INDEX
    Explanations

    elements related to audience engagement and connection

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

    "us," "people," or "public."

    np_acts-logits-general · gemini-2.0-flash

    audience words

    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
     pe
    -0.28
    ={`
    -0.27
     belong
    -0.27
    tonsoft
    -0.27
     pebbles
    -0.27
     suite
    -0.26
     fichas
    -0.26
    ˏ
    -0.26
     aplique
    -0.26
     manipulation
    -0.25
    POSITIVE LOGITS
    DockStyle
    0.67
    ValueStyle
    0.63
    setVerticalGroup
    0.62
     invokingState
    0.61
    antası
    0.59
    蚪
    0.59
    AntiForgeryToken
    0.58
    Vidite
    0.58
    FunctionFlags
    0.58
    domada
    0.56
    Activations Density 0.492%

    No Known Activations