© 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. 19-GEMMASCOPE-RES-16K
    6. 3485
    Prev
    Next
    INDEX
    Explanations

    words related to pain and its management, including forms of the word "pain" and references to painting as a metaphor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.64
    httphttps
    -0.58
    เดียว
    -0.56
    +#+#
    -0.56
    ariat
    -0.55
    vių
    -0.54
     <<<<<<<<<<<<<<
    -0.54
    Witam
    -0.53
    ductory
    -0.52
    esModule
    -0.51
    POSITIVE LOGITS
    brush
    0.93
     paints
    0.89
     Paints
    0.86
    painted
    0.82
     Paint
    0.82
     paint
    0.81
     painted
    0.80
    brushes
    0.78
     Painted
    0.78
     PAINT
    0.78
    Activations Density 0.139%

    No Known Activations