© 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 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. 16345
    Prev
    Next
    INDEX
    Explanations

    past tense verbs, particularly referring to actions and events

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

    Follows a form of "be" ("was", "were", etc.)

    np_acts-logits-general · gemini-2.0-flash

    forms of 'to be' + adjective or participle

    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
    vician
    -0.52
     belonging
    -0.46
     angekommen
    -0.46
     CWE
    -0.46
    conomie
    -0.43
     defire
    -0.43
    webElementXpaths
    -0.43
     getArguments
    -0.43
    setPreferred
    -0.43
     Belong
    -0.42
    POSITIVE LOGITS
    Autoritní
    0.73
    Personendaten
    0.67
    /**
    0.67
    WebServlet
    0.64
    httphttps
    0.58
    RTLI
    0.58
    yarnpkg
    0.57
    MigrationBuilder
    0.57
     strict
    0.57
     lenient
    0.57
    Activations Density 0.311%

    No Known Activations