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. 9605
    Prev
    Next
    INDEX
    Explanations

    references to physical injuries and their impact on individuals

    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
     idea
    -0.46
    chere
    -0.45
     idé
    -0.43
    かが
    -0.42
    StoryboardSegue
    -0.42
    Idea
    -0.42
    なのに
    -0.41
     Reich
    -0.41
     asse
    -0.40
    viously
    -0.40
    POSITIVE LOGITS
     unavoidable
    1.31
     inevitable
    1.20
     hoort
    1.13
    inev
    0.98
     Happens
    0.97
     inev
    0.95
     inevit
    0.95
    仕方ない
    0.92
     طبیعی
    0.89
     humaine
    0.89
    Activations Density 0.311%

    No Known Activations