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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 11100
    Prev
    Next
    INDEX
    Explanations

    keywords related to bugs and reproducibility in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.78
    AndEndTag
    -0.74
    MLLoader
    -0.63
    burberry
    -0.63
     Efq
    -0.62
     متعلقه
    -0.58
     Riproduzione
    -0.57
    aarrggbb
    -0.57
    EnableWeb
    -0.55
     SafeMath
    -0.55
    POSITIVE LOGITS
     tapasztal
    0.56
    Datuak
    0.52
    結果
    0.51
    歴
    0.48
    idenz
    0.48
    reprodu
    0.47
     reproducible
    0.46
    ポ
    0.46
     betweenstory
    0.46
     po
    0.46
    Activations Density 2.360%

    No Known Activations