© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 7184
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their conjugations in specific contexts, particularly in relation to sentence structure and grammar

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marín
    -0.48
    lüssel
    -0.43
     Michoacán
    -0.42
     Riti
    -0.42
     learn
    -0.41
     Fernsehen
    -0.41
    \
    -0.40
     Benoit
    -0.39
     u
    -0.39
     maal
    -0.39
    POSITIVE LOGITS
    IndentedString
    0.82
    RegressionTest
    0.78
    jspx
    0.72
    EndProject
    0.68
    RetentionPolicy
    0.67
    IsMutable
    0.66
     estekak
    0.66
    thâu
    0.66
    Jeografia
    0.65
    dafx
    0.65
    Activations Density 0.034%

    No Known Activations