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. 12437
    Prev
    Next
    INDEX
    Explanations

    various elements of source code related to database actions and configurations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     lunedì
    -0.60
    GraphicsUnit
    -0.58
     Sixteenth
    -0.56
     Monday
    -0.54
     Saturday
    -0.53
     lunes
    -0.53
     SATURDAY
    -0.52
    veri
    -0.51
     FetchType
    -0.51
     sábado
    -0.50
    POSITIVE LOGITS
            
    1.21
     Third
    1.07
     III
    1.07
     third
    1.05
    3
    1.00
     trio
    0.97
    Third
    0.97
     Wednesday
    0.96
     Drittel
    0.95
    third
    0.95
    Activations Density 0.149%

    No Known Activations