© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14990
    Prev
    Next
    INDEX
    Explanations

    references to plugins, particularly for the Firefox browser

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

    hyphenated compound words and technical terms, particularly those containing "plug-in" or similar hyphenated software/tool terminology.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    references to software plugins or extensions in technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of software plugins or extensions (especially browser add-ons like those for Firefox) and their installation or usage contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovna
    -0.38
     상세
    -0.35
    labelledby
    -0.34
     Cairo
    -0.33
     Roskov
    -0.33
    styleType
    -0.32
    Попис
    -0.32
    meneu
    -0.31
    ITERIA
    -0.30
     abstracted
    -0.29
    POSITIVE LOGITS
     plugin
    1.53
     plug
    1.36
    插件
    1.34
     plugins
    1.31
    plugin
    1.30
     Plugin
    1.29
     extension
    1.24
    Plugin
    1.22
     Extension
    1.20
     PLUG
    1.18
    Activations Density 0.540%

    No Known Activations