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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 65138
    Prev
    Next
    INDEX
    Explanations

    references to toys and their safety standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    toy descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    rungsseite
    -0.51
    +#+#
    -0.51
     zijne
    -0.48
    riceps
    -0.48
     Paglinawan
    -0.47
    \{\\
    -0.46
    loem
    -0.44
    GIVEREF
    -0.44
     ExecuteAsync
    -0.43
     Constitution
    -0.43
    POSITIVE LOGITS
     toys
    0.93
     toy
    0.75
     Toys
    0.73
    toys
    0.65
    Toys
    0.60
    玩具
    0.60
     kids
    0.60
     mainan
    0.59
    toy
    0.58
     juguetes
    0.57
    Activations Density 0.017%

    No Known Activations