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. 56812
    Prev
    Next
    INDEX
    Explanations

    terms related to giveaways and contests

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

    winning contests and giveaways

    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
    rekli
    -0.33
     muka
    -0.33
     flechas
    -0.31
     atenta
    -0.30
    enfone
    -0.30
    sividad
    -0.30
    ภู
    -0.30
     paisaje
    -0.30
     sonra
    -0.29
     Faites
    -0.29
    POSITIVE LOGITS
     giveaway
    0.77
     giveaways
    0.67
     Giveaway
    0.65
    Giveaway
    0.59
     raffle
    0.57
    awaiter
    0.55
    oneofs
    0.54
     مرئيه
    0.54
    gewin
    0.51
    chooser
    0.51
    Activations Density 0.004%

    No Known Activations