© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56265
    Prev
    Next
    INDEX
    Explanations

    terms related to overriding settings or behaviors in a configuration context

    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
     Belo
    -0.60
    eled
    -0.60
    ch
    -0.59
    koku
    -0.57
     Beans
    -0.55
     vě
    -0.54
     ch
    -0.54
     getB
    -0.54
     k
    -0.54
    WEBPACK
    -0.54
    POSITIVE LOGITS
     overrides
    1.30
    Override
    1.27
     Override
    1.21
    overrides
    1.20
     Overrides
    1.15
    verride
    1.10
    bootstrapcdn
    1.09
     overriding
    1.06
    Overrides
    1.05
     override
    1.03
    Activations Density 0.019%

    No Known Activations