© 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. 2538
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "how."

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

    "How" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    how to

    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
     дописавши
    -0.91
    Personensuche
    -0.87
     unknownFields
    -0.76
    VersionUID
    -0.75
    IntoConstraints
    -0.74
     Cæsar
    -0.74
    IVEREF
    -0.74
    BASEPATH
    -0.71
    DotNetBar
    -0.69
    SceneManagement
    -0.69
    POSITIVE LOGITS
     much
    0.92
     exactly
    0.85
     we
    0.85
     they
    0.83
     how
    0.73
     best
    0.69
     to
    0.69
    much
    0.66
    exactly
    0.65
     far
    0.65
    Activations Density 0.089%

    No Known Activations