© 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. 10542
    Prev
    Next
    INDEX
    Explanations

    punctuation marks followed by specific constructs or formatting patterns in programming code

    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
     rec
    -0.42
     iner
    -0.41
     tabu
    -0.38
     архивлан
    -0.37
     perm
    -0.35
     jud
    -0.35
     incom
    -0.35
    Cubit
    -0.34
    WritableDatabase
    -0.33
     TType
    -0.33
    POSITIVE LOGITS
    google
    0.71
    github
    0.56
    sun
    0.55
    OGND
    0.55
    fasterxml
    0.54
     GOOGLE
    0.54
    ftagPool
    0.54
    谷歌
    0.53
     EconPapers
    0.52
    Portály
    0.51
    Activations Density 0.040%

    No Known Activations