© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 6706
    Prev
    Next
    INDEX
    Explanations

    references to Shakespeare and his works, particularly famous quotes or play titles.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    references to existential questions or dilemmas

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

    Shakespeare quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    MessageTagHelper
    -0.50
     disambiguazione
    -0.48
    ouac
    -0.47
    verwijspagina
    -0.45
    řev
    -0.43
     Fahrer
    -0.42
     tár
    -0.41
     Zähne
    -0.41
    liesslich
    -0.41
     CreateTagHelper
    -0.41
    POSITIVE LOGITS
     Shakespeare
    0.96
    Shakespeare
    0.92
     Elizabethan
    0.70
    kespeare
    0.69
     Shakes
    0.68
    Hamlet
    0.57
     Hamlet
    0.54
    kespea
    0.54
     Stratford
    0.54
     Shake
    0.51
    Activations Density 0.021%

    No Known Activations