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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 977
    Prev
    Next
    INDEX
    Explanations

    references to compliance and security protocols

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

    Follows possessive pronouns ("its", "her")

    np_acts-logits-general · gemini-2.0-flash

    services, rights, ID, changes, forms

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     voc
    -0.42
    Diwedd
    -0.40
     Савезне
    -0.40
    CUR
    -0.40
    :✨
    -0.37
    Abp
    -0.37
     Photocase
    -0.36
     Gug
    -0.36
    than
    -0.36
    kla
    -0.35
    POSITIVE LOGITS
    LookAnd
    0.69
     propOrder
    0.66
     HttpNotFound
    0.62
    richTextPanel
    0.59
    Geplaatst
    0.57
     للمعارف
    0.57
    fromnode
    0.56
    ✨:
    0.56
    IntoConstraints
    0.56
    endcsname
    0.56
    Activations Density 0.853%

    No Known Activations