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. 561
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and statistical concepts

    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
    SequentialGroup
    -0.51
    Passive
    -0.48
     hos
    -0.47
     VizieR
    -0.46
    hdessä
    -0.45
    tirol
    -0.44
    covo
    -0.44
     batter
    -0.43
     跳转至
    -0.43
    ransition
    -0.43
    POSITIVE LOGITS
    sqrt
    1.91
     sqrt
    1.78
     root
    1.70
     √
    1.64
    √
    1.64
     Root
    1.55
    root
    1.54
    Sqrt
    1.48
     racine
    1.48
    Root
    1.47
    Activations Density 0.945%

    No Known Activations