© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12943
    Prev
    Next
    INDEX
    Explanations

    elements of communication, particularly focusing on listening, speaking, and the significance of what is being said

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

    Words/pronouns preceding speech or expression

    np_acts-logits-general · gemini-2.0-flash

    say something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jstor
    -0.50
     Recu
    -0.46
    lanan
    -0.45
     nahilalakip
    -0.44
    riga
    -0.44
     Preferencias
    -0.43
    ValueGeneration
    -0.43
     pinch
    -0.43
    meteor
    -0.43
     Aussch
    -0.43
    POSITIVE LOGITS
     speak
    1.21
     speaking
    1.07
     Speak
    1.05
    speak
    1.03
     speech
    1.00
    speaking
    0.98
    Speak
    0.94
     utterance
    0.94
     voice
    0.93
     speaks
    0.93
    Activations Density 0.222%

    No Known Activations