Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43267
    Prev
    Next
    INDEX
    Explanations

    actions and verbs related to taking or carrying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InitVars
    -0.81
    脚注の使い方
    -0.76
    原始内容存档于
    -0.73
    InSection
    -0.72
     AppBar
    -0.71
    addCriterion
    -0.71
    ưỡi
    -0.70
     Universitaria
    -0.67
    QSize
    -0.67
     SafeMath
    -0.66
    POSITIVE LOGITS
    يح
    0.58
     дописавши
    0.56
     terle
    0.53
     bezeichneter
    0.52
    ഞ
    0.49
     تحد
    0.49
    فاض
    0.44
    PickerController
    0.43
     åt
    0.43
    もとも
    0.43
    Activations Density 0.156%

    No Known Activations