© 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. 8-GEMMASCOPE-RES-16K
    6. 9342
    Prev
    Next
    INDEX
    Explanations

    instances of the word "talk" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MacLeod
    -0.80
    டன்
    -0.80
     Bateman
    -0.79
     Bowden
    -0.74
    SpringRunner
    -0.74
     MacMillan
    -0.73
     partij
    -0.72
    Variante
    -0.72
     leveren
    -0.72
     Hendrix
    -0.72
    POSITIVE LOGITS
     talk
    1.95
    talk
    1.84
     talks
    1.75
     TALK
    1.74
     Talk
    1.72
    Talk
    1.64
     talked
    1.64
     talking
    1.62
    TALK
    1.58
     Talks
    1.55
    Activations Density 0.051%

    No Known Activations