Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 29728
    Prev
    Next
    INDEX
    Explanations

    articles and other function words commonly used in sentences

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

    the followed by noun

    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
    RTLD
    -0.49
     pinulongan
    -0.45
    QMetaType
    -0.43
    ِّف
    -0.43
    SharedCtor
    -0.40
    oredCriteria
    -0.39
     goose
    -0.38
    Tem
    -0.37
    XmlEnum
    -0.37
    figer
    -0.36
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.75
     Signalez
    0.66
    MemoryWarning
    0.63
     defaultstate
    0.56
     estekak
    0.55
     CreateTagHelper
    0.51
     AssemblyProduct
    0.50
     שוליים
    0.50
    日閲覧
    0.48
     تكبرها
    0.48
    Activations Density 0.019%

    No Known Activations