Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16227
    Prev
    Next
    INDEX
    Explanations

    phrases related to various forms of communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yně
    -0.32
     invitado
    -0.31
     inversiones
    -0.31
    hadiran
    -0.30
     kisah
    -0.29
    OLOGÍA
    -0.29
     TAMBÉM
    -0.29
     achtergrond
    -0.29
     autonomía
    -0.29
     Verpflichtung
    -0.29
    POSITIVE LOGITS
     communication
    2.98
     communications
    2.63
    communication
    2.59
     Communication
    2.59
    Communication
    2.53
     communicate
    2.45
     COMMUNICATION
    2.42
     communicating
    2.38
     comunic
    2.31
     Kommunikation
    2.25
    Activations Density 0.490%

    No Known Activations