© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 3670
    Prev
    Next
    INDEX
    Explanations

    elements related to file structures and paths in code or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.70
     المعيارى
    -0.65
     елның
    -0.64
     متعلقه
    -0.62
    principalColumn
    -0.61
    VolleyError
    -0.59
    WriteLiteral
    -0.57
     विश्वसनीयता
    -0.52
    addCriterion
    -0.51
    ISupport
    -0.51
    POSITIVE LOGITS
     src
    0.96
    src
    0.95
     README
    0.84
    README
    0.78
     "..\..\..\
    0.70
     LICENSE
    0.70
    LICENSE
    0.67
    CHANG
    0.66
    出版年
    0.61
    index
    0.61
    Activations Density 0.372%

    No Known Activations