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. 20-GEMMASCOPE-RES-16K
    6. 712
    Prev
    Next
    INDEX
    Explanations

    specialized coding syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.66
    談社
    -0.64
    SequentialGroup
    -0.54
    AndEndTag
    -0.51
    <?
    -0.50
     Wicidata
    -0.50
     IndexError
    -0.49
     <=",
    -0.48
    Glej
    -0.48
     oprot
    -0.48
    POSITIVE LOGITS
    2
    0.98
    1
    0.94
    3
    0.90
    4
    0.75
     estimés
    0.66
     
    0.64
    2
    0.61
     تضيفلها
    0.60
     дописавши
    0.59
    5
    0.58
    Activations Density 0.866%

    No Known Activations