© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1059
    Prev
    Next
    INDEX
    Explanations

    instances of the word "talk" and its variations, indicating a focus on discussions or conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.90
    enderror
    -0.85
     veicolo
    -0.81
    Draco
    -0.77
    SizeF
    -0.76
     leveren
    -0.75
    featureID
    -0.75
     sœurs
    -0.74
     murni
    -0.72
     Soleil
    -0.72
    POSITIVE LOGITS
     talking
    2.97
     talk
    2.69
    talking
    2.67
     Talking
    2.61
    talk
    2.54
     talked
    2.54
    Talking
    2.52
     TALK
    2.51
     Talk
    2.37
     talkin
    2.28
    Activations Density 0.046%

    No Known Activations