© 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. 15-GEMMASCOPE-RES-16K
    11. 4727
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data handling expressions related to fields and requests

    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
    ↵↵
    -0.49
     far
    -0.42
     فرا
    -0.41
     Bergh
    -0.41
     Ad
    -0.40
    enumi
    -0.40
     com
    -0.39
    ย
    -0.39
    Posté
    -0.39
     utili
    -0.38
    POSITIVE LOGITS
    tagHelperRunner
    0.92
     propOrder
    0.88
    OGND
    0.87
     myſelf
    0.86
    Portale
    0.82
    HasBeenSet
    0.75
     <",
    0.75
    IsInitialized
    0.75
     Shakspeare
    0.74
    tvguidetime
    0.74
    Activations Density 0.379%

    No Known Activations