© 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. 3-GEMMASCOPE-RES-16K
    6. 15724
    Prev
    Next
    INDEX
    Explanations

    references to individuals with significant experience or qualifications in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -1.09
    yntaxException
    -0.88
    StructEnd
    -0.87
     AssemblyCulture
    -0.85
     Allociné
    -0.80
    Tembelea
    -0.80
    OrNil
    -0.79
    lgari
    -0.77
     disambiguazione
    -0.75
     crawls
    -0.75
    POSITIVE LOGITS
     experienced
    2.38
    experienced
    2.03
     Experienced
    1.98
     skilled
    1.97
    Experienced
    1.85
     seasoned
    1.64
     talented
    1.59
     knowledgeable
    1.46
    skilled
    1.44
     Skilled
    1.44
    Activations Density 0.198%

    No Known Activations