© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15739
    Prev
    Next
    INDEX
    Explanations

    references to event organization and management issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.67
     /*#__
    -0.61
    HasForeignKey
    -0.59
    UrlResolution
    -0.58
     ComVisible
    -0.57
    newtheorem
    -0.56
     TextAppearance
    -0.55
    DeleteBehavior
    -0.54
    gway
    -0.50
    corbic
    -0.49
    POSITIVE LOGITS
     organizers
    2.05
     organizing
    2.00
     organizer
    1.97
     organising
    1.90
     organisers
    1.86
     organiser
    1.82
     Organizing
    1.71
     organize
    1.67
     organizador
    1.67
    Organizing
    1.58
    Activations Density 0.321%

    No Known Activations