© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 215
    Prev
    Next
    INDEX
    Explanations

    patterns related to functions and variable definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.55
    ↵↵
    -0.54
    CloseOperation
    -0.53
     otherwise
    -0.51
    kannya
    -0.49
    >>>>>>>
    -0.48
    antar
    -0.48
    спо
    -0.48
     Stadium
    -0.48
     beseech
    -0.47
    POSITIVE LOGITS
     Lala
    0.81
     ſtate
    0.76
    знес
    0.71
     hefyd
    0.71
     culturali
    0.71
     appellants
    0.71
     bungalows
    0.69
    ValueStyle
    0.68
     Huskies
    0.66
     xenia
    0.66
    Activations Density 0.362%

    No Known Activations