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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 648
    Prev
    Next
    INDEX
    Explanations

    references to experimental methods and environments in research related to cell biology

    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
     houſe
    -0.87
     quæ
    -0.79
     محفوظة
    -0.79
     unſ
    -0.76
    Gön
    -0.74
     Majefty
    -0.74
     chré
    -0.73
     leaſt
    -0.71
     ejus
    -0.71
     ſche
    -0.71
    POSITIVE LOGITS
     vitro
    1.33
     Vitro
    1.08
     vivo
    0.91
    ActionListener
    0.60
     GenerationType
    0.57
    styleUrls
    0.56
     StatelessWidget
    0.54
     TextStyle
    0.52
     Vivo
    0.51
    ruptedException
    0.51
    Activations Density 0.030%

    No Known Activations