© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11809
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their works or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.52
    webElementXpaths
    -0.51
    StoryboardSegue
    -0.50
    GenerationType
    -0.49
    Panamoan
    -0.48
    دانشنامهٔ
    -0.47
     كومونز
    -0.46
    PageRoute
    -0.46
    UnsafeEnabled
    -0.46
    UrlResolution
    -0.45
    POSITIVE LOGITS
     TUT
    0.39
    出版年
    0.38
    jojo
    0.38
    RegressionTest
    0.38
     muñeca
    0.36
     Dud
    0.36
    nestjs
    0.35
    Jojo
    0.35
    Bab
    0.35
    Gag
    0.34
    Activations Density 0.323%

    No Known Activations