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. 19-GEMMASCOPE-RES-16K
    6. 14856
    Prev
    Next
    INDEX
    Explanations

    references to various institutes or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    туга
    -0.48
     líqu
    -0.47
    PreExecute
    -0.45
     escritas
    -0.45
    izr
    -0.45
     supervivencia
    -0.44
    IAction
    -0.42
    sprogram
    -0.42
    ื่อน
    -0.42
     escrit
    -0.42
    POSITIVE LOGITS
    fjspx
    0.80
    таратура
    0.70
    ++]=
    0.64
    سطس
    0.64
    olische
    0.64
     okuyayım
    0.63
     BoxFit
    0.62
    bezpiec
    0.62
    withstanding
    0.61
    tute
    0.61
    Activations Density 0.070%

    No Known Activations