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. 9714
    Prev
    Next
    INDEX
    Explanations

    references to subscription status and related messages

    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
     Efq
    -0.99
     pleaſure
    -0.95
    DockStyle
    -0.93
     myſelf
    -0.91
     Majefty
    -0.89
     Monfieur
    -0.88
     houſe
    -0.87
     ſeveral
    -0.87
     himſelf
    -0.86
     theater
    -0.85
    POSITIVE LOGITS
     şi
    0.86
     utilise
    0.85
     utilised
    0.81
     utilisation
    0.77
     organise
    0.75
     centre
    0.75
     apologise
    0.74
     utilising
    0.73
     recognised
    0.73
    colour
    0.72
    Activations Density 0.065%

    No Known Activations