© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 2719
    Prev
    Next
    INDEX
    Explanations

    indicators of health, well-being, and social dynamics among individuals and groups

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

    preceding auxillary verbs

    np_acts-logits-general · gemini-2.0-flash

    who describe people or groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.59
    poons
    -0.58
    LikeLike
    -0.54
    ########.
    -0.54
    httphttps
    -0.52
     skolen
    -0.51
     tjen
    -0.51
     plate
    -0.50
    async
    -0.49
     async
    -0.48
    POSITIVE LOGITS
     who
    0.87
     Those
    0.72
     those
    0.70
     ceux
    0.70
     Ceux
    0.70
     ones
    0.68
    Those
    0.65
     quienes
    0.65
    those
    0.64
    Mereka
    0.63
    Activations Density 0.613%

    No Known Activations