© 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. 8-GEMMASCOPE-RES-16K
    11. 5320
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to Angular and assembly in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.66
    <eos>
    -0.58
    <unused63>
    -0.50
     https
    -0.45
    ↵↵
    -0.45
     however
    -0.45
    MeV
    -0.44
    @
    -0.43
     golos
    -0.42
     mieux
    -0.42
    POSITIVE LOGITS
     BorderRadius
    1.63
    GraphicsUnit
    1.14
    ContentAsync
    1.09
    UrlResolution
    1.03
     Efq
    1.01
     StatefulWidget
    1.01
     TextAppearance
    0.99
     BoxDecoration
    0.94
    IntoConstraints
    0.93
    TextAppearance
    0.91
    Activations Density 0.011%

    No Known Activations