© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15509
    Prev
    Next
    INDEX
    Explanations

    code or technical documentation references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding digits, punctuation, or fragments

    np_acts-logits-general · gemini-2.0-flash

    kar, rak, ticket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.67
    WithIOException
    -0.61
    ❋
    -0.57
     jScrollPane
    -0.51
     kiện
    -0.49
    )]);
    -0.49
    SPATH
    -0.48
    "])
    -0.47
    StoryboardSegue
    -0.47
     presidenta
    -0.47
    POSITIVE LOGITS
     يتيمه
    0.60
     بيها
    0.60
    eleste
    0.58
    eroom
    0.57
    MessageTagHelper
    0.57
     Projektu
    0.54
    terdam
    0.52
     kasarigan
    0.52
     PhpStorm
    0.52
    ecin
    0.51
    Activations Density 0.065%

    No Known Activations