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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10696
    Prev
    Next
    INDEX
    Explanations

    key syntactical tokens and structural elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.62
    IntoConstraints
    -0.55
     gynhyrchwyd
    -0.54
    GEBURTSDATUM
    -0.53
    OGND
    -0.49
     cherchés
    -0.49
     ujednoznacz
    -0.49
     للاسماء
    -0.48
    __":
    -0.46
    __':
    -0.45
    POSITIVE LOGITS
    Obrázky
    0.46
    исленность
    0.44
     typelib
    0.40
    PerformLayout
    0.39
     yanı
    0.38
     isInitialized
    0.36
     CreateTagHelper
    0.36
     appartiennent
    0.36
     acost
    0.35
     maksimal
    0.35
    Activations Density 0.327%

    No Known Activations