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. 650
    Prev
    Next
    INDEX
    Explanations

    programming keywords and function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    rungsseite
    -0.90
    AddTagHelper
    -0.78
     snippetHide
    -0.66
     Paglinawan
    -0.65
     kaarangay
    -0.65
    ValueStyle
    -0.64
    TypedDataSet
    -0.63
    GOTREF
    -0.63
    存于互联网档案馆
    -0.60
    adaptiveStyles
    -0.60
    POSITIVE LOGITS
     tetapi
    0.38
     melainkan
    0.32
     BUT
    0.30
     sondern
    0.30
     but
    0.29
    composición
    0.28
     však
    0.28
     però
    0.28
    arrête
    0.28
    olden
    0.28
    Activations Density 0.011%

    No Known Activations