© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 15729
    Prev
    Next
    INDEX
    Explanations

    art-related terms that describe various forms of artistic expression and exhibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -1.18
    Personensuche
    -1.15
    GEBURTSDATUM
    -1.15
    GraphicsUnit
    -1.11
    LookAnd
    -1.09
    AddTagHelper
    -1.05
     betweenstory
    -1.05
    تقاوى
    -1.05
     oprot
    -1.04
    tagext
    -1.03
    POSITIVE LOGITS
    <eos>
    0.49
     —
    0.46
     though
    0.39
    \
    0.38
     com
    0.38
    лот
    0.37
     to
    0.36
     physical
    0.36
     ^
    0.35
     «
    0.35
    Activations Density 0.774%

    No Known Activations