© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7166
    Prev
    Next
    INDEX
    Explanations

    paragraph breaks or transitions between sections of text.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    distinct segments of text that express a range of values or categories.

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

    numerical values or code snippets.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    Preceding word ends with "t" or "s"

    np_acts-logits-general · gemini-2.0-flash

    formal or archaic wording

    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
    contentLoaded
    -0.81
    TagMode
    -0.77
     AssemblyVersion
    -0.77
    LookAnd
    -0.75
    setVerticalGroup
    -0.73
     estekak
    -0.72
    InjectAttribute
    -0.72
     MainAxisSize
    -0.68
    Personensuche
    -0.67
    WithIOException
    -0.63
    POSITIVE LOGITS
    ↵↵
    0.83
     itſelf
    0.70
     Theſe
    0.65
     Efq
    0.65
     Eſ
    0.59
     myſelf
    0.59
     Reſ
    0.58
    It
    0.58
     It
    0.58
     ſch
    0.57
    Activations Density 0.103%

    No Known Activations