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. 61766
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a description of processes or methods

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

    According to the invention

    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
    OGND
    -1.11
     utafitiHapana
    -1.00
    oneofs
    -0.95
    Diweddarwch
    -0.94
     ویکی‌پدی
    -0.92
    writeFieldEnd
    -0.90
     queſta
    -0.89
     pinulongan
    -0.89
    IUrlHelper
    -0.88
    AutoScaleMode
    -0.87
    POSITIVE LOGITS
     this
    0.43
     the
    0.33
     During
    0.26
    During
    0.25
     our
    0.23
     these
    0.23
     each
    0.23
     metu
    0.23
     Durch
    0.21
     Selama
    0.21
    Activations Density 0.021%

    No Known Activations