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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 11637
    Prev
    Next
    INDEX
    Explanations

    phrases related to business, marketing, and digital 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-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
     capitán
    -0.39
     دیکھیے
    -0.35
    CppMethod
    -0.33
    Datuak
    -0.33
    exprimer
    -0.33
    ultati
    -0.32
     iglesias
    -0.32
     ancianos
    -0.32
     Figuren
    -0.31
    praš
    -0.31
    POSITIVE LOGITS
     auffi
    0.61
     ſche
    0.60
     queſta
    0.56
    TagMode
    0.55
     verſ
    0.54
     FontWeight
    0.54
    انگلیسی
    0.53
     arşivlendi
    0.52
     pegat
    0.51
    BagLayout
    0.51
    Activations Density 0.174%

    No Known Activations