© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9521
    Prev
    Next
    INDEX
    Explanations

    terms related to caution or warnings in scientific contexts

    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
     بيها
    -0.59
    +#+#
    -0.57
     MaterialApp
    -0.51
     raisonnable
    -0.50
    IBOutlet
    -0.49
    }*/
    -0.48
    KURZBESCHREIBUNG
    -0.47
     blanches
    -0.47
     capables
    -0.47
     DialogInterface
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.72
    kháu
    0.71
     الرياضيه
    0.68
     дописавши
    0.61
    `:
    0.58
    »:
    0.58
     []:
    0.56
    !:
    0.56
     EconPapers
    0.55
    RunWith
    0.55
    Activations Density 1.300%

    No Known Activations