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. 21-GEMMASCOPE-RES-16K
    6. 2826
    Prev
    Next
    INDEX
    Explanations

    references to cellular biology and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CreateMap
    -0.75
     Wikimedijinoj
    -0.70
    onomía
    -0.70
     "..\..\
    -0.69
    RetentionPolicy
    -0.68
     otomatig
    -0.68
    yntaxException
    -0.68
     فريبيس
    -0.67
    fulness
    -0.67
    ⪢
    -0.66
    POSITIVE LOGITS
    phones
    0.89
     phone
    0.87
     cells
    0.84
    phone
    0.84
    Cells
    0.82
     phones
    0.82
    cells
    0.82
     Cells
    0.81
    ulo
    0.79
    CELL
    0.76
    Activations Density 0.173%

    No Known Activations