© 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. 11-GEMMASCOPE-RES-16K
    11. 10987
    Prev
    Next
    INDEX
    Explanations

    references to desirable or notable attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.55
     cardiaque
    -0.55
    ficulty
    -0.53
    urlpatterns
    -0.52
     włosy
    -0.52
     }))
    -0.51
     razonable
    -0.50
    arrings
    -0.50
    gulier
    -0.50
    endpush
    -0.49
    POSITIVE LOGITS
     pesky
    0.83
     thing
    0.76
     thingy
    0.68
    thing
    0.66
     thang
    0.66
     tadi
    0.65
     hanging
    0.63
    Vidite
    0.60
    あの
    0.59
     AssemblyCulture
    0.59
    Activations Density 0.184%

    No Known Activations