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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 5131
    Prev
    Next
    INDEX
    Explanations

    references to identity and cultural heritage, particularly in the context of a narrative or documentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CanadaChoose
    -0.87
    omeness
    -0.69
     تانيه
    -0.68
    NullException
    -0.64
     shrimps
    -0.63
    Jereo
    -0.63
     EconPapers
    -0.62
    ValueStyle
    -0.62
     lenker
    -0.61
     hereof
    -0.61
    POSITIVE LOGITS
     India
    0.64
    India
    0.64
     Indien
    0.55
     india
    0.53
     Indian
    0.51
     Delhi
    0.48
    Indian
    0.47
     Indias
    0.47
    Delhi
    0.46
     INDIA
    0.46
    Activations Density 0.256%

    No Known Activations