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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29532
    Prev
    Next
    INDEX
    Explanations

    elements and attributes in a structured data format, likely XML or similar markup language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    XML tags and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.58
    ént
    -0.55
    oole
    -0.52
    getColumnIndex
    -0.51
    __()
    -0.50
     surla
    -0.49
    tance
    -0.49
    ContentLoaded
    -0.49
    kotlin
    -0.48
    oa̍t
    -0.48
    POSITIVE LOGITS
    发表于
    0.87
     للمعارف
    0.70
    رشف
    0.69
     bezeichneter
    0.68
     <<<<<<<<<<<<<<
    0.67
     définiti
    0.65
     poveznice
    0.60
     ivelany
    0.59
     оригіналу
    0.59
     Akismet
    0.58
    Activations Density 0.011%

    No Known Activations