© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8969
    Prev
    Next
    INDEX
    Explanations

    terms related to public health, services, and entities

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

    "Public" (capitalized or lowercase)

    np_acts-logits-general · gemini-2.0-flash

    public health and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zdję
    -0.45
     ExecuteAsync
    -0.43
    weightedMode
    -0.42
     całym
    -0.40
     nocy
    -0.40
     moż
    -0.40
    matchCondition
    -0.39
     boneca
    -0.39
     consigo
    -0.39
    RotationOrder
    -0.39
    POSITIVE LOGITS
     Public
    0.87
    Public
    0.82
     public
    0.74
     PUBLIC
    0.69
    public
    0.64
     publicly
    0.60
     öffentliche
    0.56
    公
    0.55
     publick
    0.55
     publics
    0.54
    Activations Density 0.101%

    No Known Activations