© 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. 10-GEMMASCOPE-RES-16K
    11. 5765
    Prev
    Next
    INDEX
    Explanations

    the structure and formatting of mathematical expressions and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     censi
    -0.74
    ers
    -0.74
    ص
    -0.72
    т
    -0.71
    Ester
    -0.71
     مص
    -0.70
    oye
    -0.70
     Schuster
    -0.69
    ي
    -0.69
    er
    -0.68
    POSITIVE LOGITS
    )\
    1.28
     {}\
    1.23
    __':
    1.19
    ()\
    1.19
    }\
    1.17
    __":
    1.15
    {}\
    1.09
    '\
    1.08
     }}\
    1.06
    ']))
    1.06
    Activations Density 0.410%

    No Known Activations