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. 20-GEMMASCOPE-RES-16K
    6. 14291
    Prev
    Next
    INDEX
    Explanations

    database table creation and related SQL structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •SQL-labeled features

    No Comments

    Negative Logits
    VolleyError
    -0.60
    RectangleBorder
    -0.59
    CompleteListener
    -0.56
     desto
    -0.55
     ProductService
    -0.52
    tifkan
    -0.50
    سياسي
    -0.50
     Socorro
    -0.49
     })}
    -0.49
     Contribution
    -0.48
    POSITIVE LOGITS
     table
    1.33
     tables
    1.13
     Table
    1.07
    table
    0.98
    Table
    0.98
     TABLE
    0.94
     Tables
    0.88
     tabel
    0.87
    TABLE
    0.84
     tabela
    0.84
    Activations Density 0.247%

    No Known Activations