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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9312
    Prev
    Next
    INDEX
    Explanations

    references to national identity or governance

    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
    ItemLayout
    -0.61
    featureID
    -0.61
    цездатний
    -0.59
     tudo
    -0.52
    ParallelGroup
    -0.49
     manuscrit
    -0.49
    nologue
    -0.48
     তারিখ
    -0.47
     perang
    -0.46
    astéroïdes
    -0.45
    POSITIVE LOGITS
     people
    0.95
     participants
    0.90
     occupants
    0.87
     residents
    0.85
     owners
    0.80
     authorities
    0.77
     organisers
    0.77
     inhabitants
    0.76
     organizers
    0.76
     members
    0.75
    Activations Density 0.459%

    No Known Activations