Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 13298
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses and their contents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inſ
    -0.66
     Diſ
    -0.64
     Reſ
    -0.63
     Theſe
    -0.60
     Eſ
    -0.60
     Houſe
    -0.57
     quelque
    -0.56
    énéral
    -0.56
     Conſ
    -0.56
     Tah
    -0.55
    POSITIVE LOGITS
    rungsseite
    0.75
    lapsingToolbar
    0.74
     unknownFields
    0.70
     resourceCulture
    0.63
     (
    0.59
     BIBSYS
    0.57
    StoryboardSegue
    0.56
    GetMapping
    0.56
    RegressionTest
    0.53
     Lying
    0.53
    Activations Density 0.307%

    No Known Activations