© 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. 21-GEMMASCOPE-RES-16K
    11. 7940
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting related to non-Latin scripts, particularly Hebrew

    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
     houſe
    -1.07
     pleaſure
    -1.02
     purpoſe
    -1.00
     whoſe
    -0.88
     quæ
    -0.88
     Monfieur
    -0.88
     themſelves
    -0.87
     reaſon
    -0.86
     cauſe
    -0.86
     raiſ
    -0.85
    POSITIVE LOGITS
     ‏
    0.44
     SDM
    0.43
     UAS
    0.42
     מ
    0.41
     ע
    0.41
     NIS
    0.41
     HRS
    0.41
     כ
    0.40
     ד
    0.40
     CPO
    0.40
    Activations Density 0.001%

    No Known Activations