Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6852
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to computer systems and software

    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
    CloseOperation
    -0.59
    idom
    -0.58
     Minaj
    -0.52
     Gout
    -0.52
     espacial
    -0.51
    tamen
    -0.50
    idazole
    -0.48
     paraître
    -0.48
     XMLHttpRequest
    -0.48
     ModelExpression
    -0.47
    POSITIVE LOGITS
     boot
    1.12
    boot
    0.99
     Boot
    0.95
     booting
    0.94
    Boot
    0.90
     BOOT
    0.87
    BOOT
    0.86
     bootloader
    0.85
    ImageContext
    0.78
     boots
    0.76
    Activations Density 0.345%

    No Known Activations