© 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. 1-GEMMASCOPE-RES-16K
    6. 14492
    Prev
    Next
    INDEX
    Explanations

    references to teeth and dental terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.73
    ConstraintMaker
    -0.71
    Jeografia
    -0.67
    awtextra
    -0.66
     doInBackground
    -0.66
    Хьажоргаш
    -0.62
     يتيمه
    -0.61
    MigrationBuilder
    -0.58
     Sams
    -0.57
     prins
    -0.57
    POSITIVE LOGITS
     Gran
    1.21
    Gran
    1.13
     gran
    0.99
     GRAN
    0.89
     Early
    0.89
     teeth
    0.88
     early
    0.87
    gran
    0.86
    liminary
    0.86
    early
    0.85
    Activations Density 0.113%

    No Known Activations