© 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. 22-GEMMASCOPE-RES-16K
    11. 2527
    Prev
    Next
    INDEX
    Explanations

    references to "heavy" or heavyweight concepts, especially in various contexts

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

    "heavy"

    np_acts-logits-general · gemini-2.0-flash

    heavy metals

    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
    PreferredItem
    -0.78
    parsedMessage
    -0.72
    XmlAccessorType
    -0.70
     виправивши
    -0.69
    AndEndTag
    -0.69
    AccessorTable
    -0.63
    хьтан
    -0.62
     beginnetje
    -0.61
    __*/
    -0.59
     незавершена
    -0.58
    POSITIVE LOGITS
     duty
    1.32
    weights
    1.28
    duty
    1.21
    Heavy
    1.20
     Heavy
    1.19
     Duty
    1.17
     HEAVY
    1.17
     heavy
    1.13
    Duty
    1.13
     DUTY
    1.12
    Activations Density 0.064%

    No Known Activations