© 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. 28-GEMMASCOPE-RES-16K
    6. 4963
    Prev
    Next
    INDEX
    Explanations

    words related to roles and categories of individuals involved in various contexts

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

    Plural nouns denoting people involved in something

    np_acts-logits-general · gemini-2.0-flash

    roles in agreements or studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ActionMode
    -0.43
    reactstrap
    -0.42
    TAWA
    -0.41
    tableFuture
    -0.40
    aarrggbb
    -0.37
    TargetApi
    -0.37
    setVerticalGroup
    -0.35
     rowspan
    -0.35
     superintend
    -0.34
     internetowa
    -0.34
    POSITIVE LOGITS
     hereof
    0.59
     tæ
    0.56
    Datuak
    0.53
    PreInfinity
    0.52
     Trá
    0.51
     hjemmes
    0.51
    criptor
    0.50
    oredCriteria
    0.49
     Ejecutivo
    0.48
     メンテナ
    0.48
    Activations Density 0.803%

    No Known Activations