© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15765
    Prev
    Next
    INDEX
    Explanations

    references to sports-related teams or organizations

    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
    featureID
    -0.58
    EDEFAULT
    -0.57
     Normdatei
    -0.57
     الحره
    -0.56
    بوابة
    -0.55
    TagMode
    -0.51
    clusal
    -0.50
    setVerticalGroup
    -0.49
    Scénario
    -0.48
     invokevirtual
    -0.47
    POSITIVE LOGITS
     franchise
    0.58
    franchise
    0.56
    Batis
    0.56
    årige
    0.56
    komo
    0.54
    Cyfeiriadau
    0.53
     season
    0.52
     sponsors
    0.51
    dba
    0.51
    WillAppear
    0.50
    Activations Density 0.067%

    No Known Activations