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. 998
    Prev
    Next
    INDEX
    Explanations

    terms related to partnerships and collaborative support in the arts and community initiatives

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

    agreements, partnerships, or cooperation

    np_acts-logits-general · gemini-2.0-flash

    agreements and partnerships

    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
    parsedMessage
    -0.79
    SourceChecksum
    -0.65
    Дереккөздер
    -0.53
    ReadByte
    -0.51
    fromnode
    -0.49
    Rüyada
    -0.49
    ValueStyle
    -0.48
    modelBuilder
    -0.47
     myſelf
    -0.47
    ագրություններ
    -0.47
    POSITIVE LOGITS
     agreements
    0.44
    VersionUID
    0.40
     agreement
    0.36
     Vereinbarung
    0.35
     Agreements
    0.35
    Viited
    0.34
     согласи
    0.33
     agreeing
    0.32
    Privile
    0.32
     contracts
    0.31
    Activations Density 0.310%

    No Known Activations