© 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. 14033
    Prev
    Next
    INDEX
    Explanations

    references to consent and ethical protocols 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 @ 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
    PreferredItem
    -0.64
    ьаж
    -0.59
    prefixer
    -0.57
     يتيمه
    -0.51
     Omen
    -0.50
    rigkeit
    -0.50
     trono
    -0.50
     numerus
    -0.49
    igheid
    -0.49
     Pexels
    -0.49
    POSITIVE LOGITS
     sheet
    1.61
     document
    1.34
     sheets
    1.29
     booklet
    1.25
    sheet
    1.25
     Sheet
    1.18
    heet
    1.13
     SHEET
    1.08
     packet
    1.07
     file
    1.05
    Activations Density 1.136%

    No Known Activations