© 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. 14-GEMMASCOPE-RES-16K
    11. 15141
    Prev
    Next
    INDEX
    Explanations

    occurrences of functions and methods related to GUI component management and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    listdir
    -0.47
    RenderAtEndOf
    -0.44
     Kemen
    -0.40
     élector
    -0.37
     NotImplemented
    -0.36
    Skocz
    -0.36
    )))));
    -0.35
    intensive
    -0.35
    harvard
    -0.35
     intensively
    -0.35
    POSITIVE LOGITS
     Efq
    0.74
     purpoſe
    0.71
    IsMutable
    0.69
     houſe
    0.69
    Personendaten
    0.68
     uſe
    0.66
    MetaObject
    0.66
     greateſt
    0.66
     Majefty
    0.66
     reaſon
    0.66
    Activations Density 0.169%

    No Known Activations