© 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. 20-GEMMASCOPE-RES-16K
    11. 3726
    Prev
    Next
    INDEX
    Explanations

    instances of the word "specific" and related terms, indicating a focus on precision and clearly defined elements

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

    Followed by immunological or experimental terms

    np_acts-logits-general · gemini-2.0-flash

    specific instances or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scribers
    -0.59
     Cuen
    -0.55
    INGS
    -0.55
    ńcu
    -0.54
    ings
    -0.52
    moso
    -0.52
    eadas
    -0.52
    upat
    -0.50
    mphony
    -0.50
    està
    -0.49
    POSITIVE LOGITS
    /**
    0.75
    ities
    0.75
    /**
    0.70
    出版年
    0.68
    Geplaatst
    0.67
    ially
    0.67
    Życiorys
    0.66
    iation
    0.66
     targeting
    0.65
     details
    0.64
    Activations Density 0.153%

    No Known Activations