© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13572
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as brackets, braces, and control flow statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſeveral
    -0.84
     myſelf
    -0.76
     houſe
    -0.74
     greateſt
    -0.73
     Monfieur
    -0.71
     purpoſe
    -0.71
    modelBuilder
    -0.70
     themſelves
    -0.70
     ſtate
    -0.70
     itſelf
    -0.69
    POSITIVE LOGITS
     disambiguazione
    0.57
    出版年
    0.54
    Nuorodos
    0.51
    LabelTagHelper
    0.51
     Meksiku
    0.49
    ագրություններ
    0.49
    рованной
    0.48
    Istorija
    0.48
    withIdentifier
    0.47
     .$
    0.46
    Activations Density 0.172%

    No Known Activations