© 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. 21-GEMMASCOPE-RES-16K
    11. 11731
    Prev
    Next
    INDEX
    Explanations

    instances of social interactions and communication dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ęcia
    -0.47
    culable
    -0.44
    ropriate
    -0.44
    myra
    -0.43
    tomation
    -0.43
    zeigen
    -0.43
    đu
    -0.42
     Chwiliwch
    -0.42
    mitives
    -0.41
    ikka
    -0.41
    POSITIVE LOGITS
     listening
    3.08
     listen
    2.98
     listened
    2.85
     listens
    2.77
     Listen
    2.67
     Listening
    2.64
     hearing
    2.59
    listening
    2.51
     listener
    2.50
    Listening
    2.50
    Activations Density 0.339%

    No Known Activations