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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 366
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or terms related to medical conditions or anatomical components

    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
     око
    -0.33
    wide
    -0.32
     goc
    -0.32
     bewe
    -0.31
    Луч
    -0.30
    s
    -0.30
     sem
    -0.29
    WIDE
    -0.29
    width
    -0.28
     univers
    -0.28
    POSITIVE LOGITS
     contextLoads
    0.79
    rungsseite
    0.74
    MigrationBuilder
    0.73
    Hentet
    0.73
     surla
    0.72
    StoryboardSegue
    0.71
    EndInit
    0.71
    脚注の使い方
    0.69
    expandindo
    0.68
    OGND
    0.67
    Activations Density 0.232%

    No Known Activations