© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2941
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "talk" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.52
     ſta
    -0.51
     Noire
    -0.47
     Wikiseite
    -0.46
     évêque
    -0.46
    ftagPool
    -0.44
    Revelation
    -0.44
     Perſ
    -0.43
     viceversa
    -0.43
     privées
    -0.42
    POSITIVE LOGITS
     talk
    0.92
     Talk
    0.75
    Talk
    0.69
    talk
    0.69
    хьтан
    0.62
     propOrder
    0.59
    LookAnd
    0.57
     autorytatywna
    0.56
    TALK
    0.51
     hey
    0.49
    Activations Density 0.235%

    No Known Activations