© 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. 4-GEMMASCOPE-RES-16K
    6. 13314
    Prev
    Next
    INDEX
    Explanations

    definite articles and their grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bit
    -0.55
    ροφο
    -0.54
     potr
    -0.53
     team
    -0.53
     Vicky
    -0.52
     opat
    -0.51
     cof
    -0.51
    Vicky
    -0.50
     gad
    -0.50
     Πε
    -0.50
    POSITIVE LOGITS
     den
    2.32
    Den
    2.28
     Den
    2.24
     DEN
    2.15
    den
    1.88
    DEN
    1.78
     Denison
    1.37
     unseren
    1.34
     seinen
    1.32
     meinen
    1.31
    Activations Density 0.079%

    No Known Activations