© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 15668
    Prev
    Next
    INDEX
    Explanations

    references to specific web development frameworks or libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.97
    +#+#
    -0.88
     CreateTagHelper
    -0.85
     gynhyrchwyd
    -0.83
    Portale
    -0.82
    Portail
    -0.81
    StoryboardSegue
    -0.81
     Paglinawan
    -0.79
    KEYCODE
    -0.79
    ANTLR
    -0.79
    POSITIVE LOGITS
     groupBox
    1.86
    groupBox
    1.78
    GroupBox
    1.44
    Holmes
    0.76
     Holmes
    0.75
    bní
    0.66
    ţele
    0.64
     cloche
    0.60
    Groups
    0.60
    fieldset
    0.58
    Activations Density 0.002%

    No Known Activations