© 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. 22-GEMMASCOPE-RES-16K
    11. 10710
    Prev
    Next
    INDEX
    Explanations

    references to government agencies and regulatory bodies

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

    Governmental agencies or bodies

    np_acts-logits-general · gemini-2.0-flash

    government agencies and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.66
     surla
    -0.60
    LookAnd
    -0.59
     للمعارف
    -0.57
    ValueStyle
    -0.56
    complexContent
    -0.55
    MemoryWarning
    -0.54
    MediaStore
    -0.53
    LLocation
    -0.53
     SafeMath
    -0.53
    POSITIVE LOGITS
     agencies
    1.46
     organizations
    1.31
     bodies
    1.31
     institutions
    1.30
     agency
    1.28
     organisations
    1.27
     institution
    1.23
     body
    1.20
     organization
    1.19
     organisation
    1.16
    Activations Density 0.281%

    No Known Activations