© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-GEMMASCOPE-RES-16K
    11. 9429
    Prev
    Next
    INDEX
    Explanations

    discussions about limitations and challenges in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.65
     MotionEvent
    -0.63
    oa̍t
    -0.60
     nawr
    -0.59
    tangentMode
    -0.58
     Lightboxes
    -0.55
    kháu
    -0.53
     Washable
    -0.53
    Demografie
    -0.51
     iNdEx
    -0.51
    POSITIVE LOGITS
     lack
    2.73
    Lack
    2.21
     Lack
    2.15
    lack
    2.12
     insufficient
    1.94
     inadequate
    1.90
     poor
    1.77
     lacking
    1.76
     manque
    1.76
     falta
    1.75
    Activations Density 1.188%

    No Known Activations