© 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. 22-GEMMASCOPE-RES-16K
    11. 14945
    Prev
    Next
    INDEX
    Explanations

    statements or phrases related to speech and communication

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

    being spoken or uttered

    np_acts-logits-general · gemini-2.0-flash

    spoken words and sayings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     küm
    -0.54
    ItemLayout
    -0.54
     toán
    -0.53
     sơ
    -0.53
     bParam
    -0.52
    Inflater
    -0.52
    OrNil
    -0.51
    LError
    -0.51
    Jeografia
    -0.50
    Istorija
    -0.50
    POSITIVE LOGITS
     uttered
    1.69
     uttering
    1.54
     utterance
    1.47
     spoken
    1.26
     utterances
    1.20
     words
    1.19
     Spoken
    1.11
    Spoken
    1.10
    spoken
    1.08
     pronounce
    1.05
    Activations Density 0.400%

    No Known Activations