© 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. 25-GEMMASCOPE-RES-16K
    11. 14435
    Prev
    Next
    INDEX
    Explanations

    content related to copyright and permissions for software or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.52
    ifolia
    -0.49
    Regressor
    -0.48
     Deckel
    -0.45
     autorytatywna
    -0.44
     &___
    -0.44
    PreExecute
    -0.44
    省市镇
    -0.43
    appBar
    -0.43
    fiez
    -0.42
    POSITIVE LOGITS
     redistribution
    1.00
     reproduction
    0.88
     redistribute
    0.88
     Reproduce
    0.86
     Redist
    0.86
     reproduce
    0.84
     repub
    0.83
     reproducing
    0.82
     reproductions
    0.78
     reproduced
    0.78
    Activations Density 0.593%

    No Known Activations