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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5265
    Prev
    Next
    INDEX
    Explanations

    specific dates and events related to the Shanti Bahini organization

    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-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
     للاسماء
    -1.02
     queſta
    -0.88
    <unused3>
    -0.84
    <unused41>
    -0.83
    <unused17>
    -0.83
    <unused8>
    -0.83
    <unused52>
    -0.83
    <unused74>
    -0.83
    <unused42>
    -0.83
    <unused14>
    -0.83
    POSITIVE LOGITS
    1
    0.38
     
    0.35
     Haare
    0.35
     Gnade
    0.33
    .
    0.33
    GOTREF
    0.32
     Naciones
    0.32
     Certainly
    0.32
     teda
    0.31
     Angabe
    0.31
    Activations Density 0.969%

    No Known Activations