© 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. 3-GEMMASCOPE-RES-16K
    11. 8952
    Prev
    Next
    INDEX
    Explanations

    lines that comment code, particularly using syntax for comments and preprocessor directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.54
    )}</
    -0.50
    "],
    -0.48
    ​=
    -0.48
     solares
    -0.47
    큼
    -0.47
    Schul
    -0.46
    uments
    -0.45
     slab
    -0.45
    ])):
    -0.44
    POSITIVE LOGITS
    Personensuche
    0.96
     Wikimedijinoj
    0.79
    withIdentifier
    0.75
     незавершена
    0.73
    //
    0.71
     يتيمه
    0.67
    цездатний
    0.66
     BoxFit
    0.65
    LabelTagHelper
    0.65
    PutMapping
    0.65
    Activations Density 0.472%

    No Known Activations