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. 6445
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in alphanumeric sequences

    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
     bezeichneter
    -0.68
    setupUi
    -0.66
    lages
    -0.56
    nsis
    -0.52
     виправивши
    -0.52
    chee
    -0.51
     grandmother
    -0.51
    cheese
    -0.51
    gonic
    -0.51
     Kinney
    -0.51
    POSITIVE LOGITS
    4
    1.61
     Fourth
    1.43
     fourth
    1.39
    Fourth
    1.32
     four
    1.21
     Four
    1.20
     keempat
    1.19
    fourth
    1.19
     FOURTH
    1.19
    4
    1.15
    Activations Density 1.203%

    No Known Activations