© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3415
    Prev
    Next
    INDEX
    Explanations

    patterns of conditional phrases and expressions of uncertainty

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

    "Always" or "Never"

    np_acts-logits-general · gemini-2.0-flash

    never or always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    DataAnnotations
    -0.56
    ungkinan
    -0.52
     rospy
    -0.48
    isantes
    -0.48
     '{@
    -0.47
    </thead>
    -0.47
    ocu
    -0.46
     AssemblyCulture
    -0.45
    LookAnd
    -0.45
     otomatig
    -0.45
    POSITIVE LOGITS
     never
    3.23
     always
    3.15
    never
    2.95
    always
    2.93
     Never
    2.85
     Always
    2.80
    Never
    2.79
    Always
    2.79
     nigdy
    2.75
     NEVER
    2.65
    Activations Density 0.608%

    No Known Activations