© 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. 38276
    Prev
    Next
    INDEX
    Explanations

    the presence of specific structural or organizational markers related to data or entities

    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
    SuccessListener
    -0.53
    -------------</
    -0.51
    chyma
    -0.50
    лыша
    -0.48
     sauvages
    -0.46
     esboço
    -0.45
     way
    -0.45
     Chwiliwch
    -0.44
    upstream
    -0.44
    進
    -0.42
    POSITIVE LOGITS
    __*/
    0.76
     protoimpl
    0.75
    tagHelperRunner
    0.74
    مصادر
    0.69
    yorsunuz
    0.67
    Посилання
    0.66
    KommentareTeilen
    0.65
     mergeFrom
    0.65
    Datuak
    0.64
    Erreferentziak
    0.64
    Activations Density 0.131%

    No Known Activations