© 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 - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 13251
    Prev
    Next
    INDEX
    Explanations

    references to personal backgrounds and life events of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scelte
    -0.43
     new
    -0.39
    findpost
    -0.38
    richTextPanel
    -0.38
     excepción
    -0.38
    -------------</
    -0.38
    setPower
    -0.36
    Aholisi
    -0.35
     mondial
    -0.35
    ">//
    -0.35
    POSITIVE LOGITS
    Geplaatst
    0.79
    TemporalType
    0.72
    RectangleBorder
    0.71
     MessageBoxIcon
    0.71
    AddTagHelper
    0.71
     
    0.69
     >=",
    0.69
    SizeF
    0.68
    drawSprites
    0.65
     TextAppearance
    0.65
    Activations Density 0.317%

    No Known Activations