© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14964
    Prev
    Next
    INDEX
    Explanations

    specific patterns in code or markup, particularly related to class definitions and database connections within a Django framework context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reactstrap
    -0.43
    ฬ
    -0.41
     developed
    -0.41
     dasarnya
    -0.39
     inter
    -0.37
     remember
    -0.37
     تكبرها
    -0.36
    aly
    -0.36
    gisi
    -0.36
     граждан
    -0.36
    POSITIVE LOGITS
    RTDA
    1.02
    rungsseite
    0.85
    ={`/
    0.75
    TypedDataSet
    0.69
     BoxDecoration
    0.67
     DTS
    0.64
    AnchorStyles
    0.64
     myſelf
    0.63
     Dodo
    0.62
     subsoil
    0.61
    Activations Density 0.477%

    No Known Activations