© 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. 17-GEMMASCOPE-RES-16K
    6. 4645
    Prev
    Next
    INDEX
    Explanations

    clauses describing definitions or classifications of terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    раздо
    -0.49
    Tembelea
    -0.48
    LElement
    -0.46
     scalability
    -0.45
    ultuous
    -0.45
     Wicidata
    -0.45
    YOND
    -0.45
     Valerie
    -0.44
     freedom
    -0.44
    hipping
    -0.43
    POSITIVE LOGITS
     signs
    1.42
    Signs
    1.34
     indicators
    1.33
     Signs
    1.30
     indicator
    1.29
     Indicators
    1.26
    signs
    1.16
    Indicators
    1.14
     SIGNS
    1.11
    indicator
    1.08
    Activations Density 0.521%

    No Known Activations