© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11566
    Prev
    Next
    INDEX
    Explanations

    words related to legal and regulatory implications

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

    words with the prefix or root "command" or "commande" and similar action verbs indicating dominance or control.

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

    words ending in common suffixes like "-ize", "-izing", "-ise", and "-ising" that indicate action or process.

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

    the roots or prefixes of long, morphologically complex (often Latinate/Greek) words, especially at the start of verbs and derived nouns.

    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
    LookAnd
    -1.09
     esternos
    -0.85
    ChildScrollView
    -0.82
     AssemblyCulture
    -0.78
     للاسماء
    -0.77
    ArrowToggle
    -0.77
     geſch
    -0.75
     estadounid
    -0.75
    transQ
    -0.73
    ніципалі
    -0.73
    POSITIVE LOGITS
    ize
    0.39
    ing
    0.37
    ise
    0.32
    ed
    0.32
    ized
    0.31
    bing
    0.29
    tiliz
    0.28
    ying
    0.28
    izing
    0.27
     annot
    0.27
    Activations Density 0.476%

    No Known Activations