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. 105015
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" indicating existence or presence

    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
    「
    -0.35
    Vegeu
    -0.34
     señ
    -0.30
    Pautan
    -0.30
    číta
    -0.29
     écla
    -0.28
    Meta
    -0.27
    meta
    -0.26
     affaires
    -0.26
     inqui
    -0.25
    POSITIVE LOGITS
    ſehen
    0.74
    wiliwch
    0.74
    :✨
    0.73
    <unused41>
    0.71
    <unused16>
    0.70
    <unused14>
    0.70
    <unused17>
    0.70
    <unused28>
    0.70
    [@BOS@]
    0.70
    <unused8>
    0.70
    Activations Density 0.010%

    No Known Activations