© 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. 11-GEMMASCOPE-RES-16K
    11. 4305
    Prev
    Next
    INDEX
    Explanations

    messages related to file upload success and failure, as well as confirmation prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '},
    -0.54
    ?}",
    -0.54
    \{\\
    -0.47
    >*/
    -0.46
    agaimana
    -0.43
    ViewImports
    -0.42
    <eos>
    -0.41
     miras
    -0.39
    SharedDtor
    -0.38
     $\
    -0.37
    POSITIVE LOGITS
    addContainerGap
    0.72
    zaak
    0.68
    ivotopis
    0.64
     переписи
    0.64
    dataflow
    0.63
    قایناقلار
    0.62
    Boletín
    0.62
    ystema
    0.60
     leksikon
    0.59
     Jahrhundert
    0.59
    Activations Density 0.139%

    No Known Activations