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. 3562
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with completed surveys and account management

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

    listing sender or resources

    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
    Geplaatst
    -0.38
    こ
    -0.36
    GUS
    -0.36
    guh
    -0.35
    stay
    -0.35
    bild
    -0.35
    もしれない
    -0.35
    ByPrimaryKey
    -0.34
     Stay
    -0.34
    aus
    -0.34
    POSITIVE LOGITS
     EconPapers
    0.61
     &___
    0.53
    ]")]
    0.53
    WireFormat
    0.52
     Paglinawan
    0.50
     بيها
    0.49
    évaluateur
    0.49
    CppMethod
    0.48
     transporters
    0.48
    AndEndTag
    0.48
    Activations Density 0.023%

    No Known Activations