© 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. 11486
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure in Java programming language documentation

    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
     transcrip
    -0.45
     prote
    -0.44
     abs
    -0.38
     secre
    -0.36
     om
    -0.33
    🕒
    -0.33
     star
    -0.32
    󠁿
    -0.31
     dé
    -0.30
     ab
    -0.29
    POSITIVE LOGITS
     Math
    1.24
    Math
    1.20
     Integer
    1.02
     Object
    1.01
    Integer
    0.96
    Object
    0.94
     Mathematical
    0.75
    Double
    0.71
     Character
    0.70
     Double
    0.69
    Activations Density 0.207%

    No Known Activations