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. 22-GEMMASCOPE-RES-16K
    6. 13929
    Prev
    Next
    INDEX
    Explanations

    elements related to networking protocols and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NTB
    -0.68
     Rijks
    -0.67
     Hajj
    -0.67
     Krone
    -0.65
    Rij
    -0.61
     Steer
    -0.61
     Beetle
    -0.60
    autique
    -0.59
     '\\;'
    -0.59
     Cain
    -0.59
    POSITIVE LOGITS
     SOL
    1.94
     Sol
    1.93
    Sol
    1.84
     sol
    1.80
    SOL
    1.77
    sol
    1.68
     Soli
    1.46
     socket
    1.46
     Socket
    1.45
    ソ
    1.43
    Activations Density 0.282%

    No Known Activations