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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1471
    Prev
    Next
    INDEX
    Explanations

    references to societal issues and criticisms

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

    evaluative, opinionated statements that make broad judgments about people, society, or topics—praising, criticizing, or reflecting on what something is about.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.75
     autorytatywna
    -0.72
     propOrder
    -0.62
    ſicht
    -0.60
     Geiſt
    -0.59
     erſten
    -0.58
    wiliwch
    -0.57
    ſelben
    -0.57
     ſuo
    -0.56
     queſto
    -0.56
    POSITIVE LOGITS
     Zoo
    0.35
     Wave
    0.32
    currentColor
    0.32
    zoo
    0.32
     these
    0.32
     S
    0.31
     always
    0.30
     p
    0.30
     used
    0.30
    越来越
    0.30
    Activations Density 0.352%

    No Known Activations