© 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. 15-GEMMASCOPE-RES-16K
    11. 5712
    Prev
    Next
    INDEX
    Explanations

    references to function parameters, their types, and how they are used in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ?>>
    -0.68
    Демографія
    -0.63
    setVerticalGroup
    -0.61
     Normdatei
    -0.60
    VIAF
    -0.60
    ChildScrollView
    -0.60
    kuuta
    -0.59
     makers
    -0.59
     فريبيس
    -0.56
    CrossOrigin
    -0.56
    POSITIVE LOGITS
     arguments
    0.77
    arg
    0.74
    GEBURTS
    0.73
     getArguments
    0.70
    Arguments
    0.69
    ingabe
    0.69
    ARG
    0.68
     argument
    0.68
    arguments
    0.65
     args
    0.65
    Activations Density 0.346%

    No Known Activations