© 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. 36-GEMMASCOPE-RES-16K
    11. 6781
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and terms relevant to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diweddarwch
    -0.41
     useAppContext
    -0.38
    wahati
    -0.35
    IsMutable
    -0.31
    Datuak
    -0.30
     unknownFields
    -0.30
     мәкал
    -0.30
    PerformLayout
    -0.29
    XmlAccessorType
    -0.29
     دیکھیے
    -0.29
    POSITIVE LOGITS
     target
    4.03
    target
    3.56
     Target
    3.42
    Target
    3.34
     targets
    3.28
     TARGET
    3.19
    TARGET
    2.95
     Targets
    2.88
    targets
    2.73
    Targets
    2.66
    Activations Density 0.980%

    No Known Activations