© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 7195
    Prev
    Next
    INDEX
    Explanations

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

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

    "talk" or its variations

    np_acts-logits-general · gemini-2.0-flash

    forms of talk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exus
    -0.83
    SourceChecksum
    -0.83
     erythrocytes
    -0.82
    BeginInit
    -0.79
     Dumont
    -0.78
     MediatR
    -0.78
     Medvedev
    -0.78
    ducer
    -0.78
     Automata
    -0.77
     Christo
    -0.76
    POSITIVE LOGITS
     talk
    1.06
    talk
    1.04
     talked
    1.00
     TALK
    0.99
    TALK
    0.86
     Talk
    0.86
     talking
    0.86
    Talk
    0.83
    talking
    0.82
     talks
    0.79
    Activations Density 0.049%

    No Known Activations