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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4682
    Prev
    Next
    INDEX
    Explanations

    references to communication and attentiveness in social interactions

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

    listening or hearing

    np_acts-logits-general · gemini-2.0-flash

    hearing and listening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikka
    -0.45
    erol
    -0.45
    ęcia
    -0.44
    gypte
    -0.42
     squee
    -0.41
    ณ์
    -0.40
    thday
    -0.40
    тельство
    -0.40
     Chwiliwch
    -0.40
    тельстве
    -0.40
    POSITIVE LOGITS
     listen
    3.00
     listening
    2.91
     hear
    2.90
     hearing
    2.80
     hears
    2.73
     listened
    2.70
     listens
    2.70
     heard
    2.66
     Listen
    2.62
     Listening
    2.46
    Activations Density 0.329%

    No Known Activations