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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6126
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events and authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vedo
    -0.61
     current
    -0.54
     I
    -0.52
     сегодняш
    -0.51
     you
    -0.51
     глоба
    -0.50
     latest
    -0.50
     Phari
    -0.50
    互联网档案馆
    -0.49
     currently
    -0.48
    POSITIVE LOGITS
     '\\;'
    0.86
    endphp
    0.75
    tonode
    0.71
    érables
    0.71
     &___
    0.70
    ---*/
    0.69
    UnknownFields
    0.68
    >*/
    0.67
     <>",
    0.67
    multer
    0.66
    Activations Density 1.691%

    No Known Activations