© 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. 21-GEMMASCOPE-RES-16K
    6. 2393
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing quality or appearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getRule
    -0.66
    DebuggerNonUser
    -0.59
     drept
    -0.53
    hingga
    -0.52
    Зноскі
    -0.52
     depoz
    -0.52
    ようになります
    -0.50
    eraard
    -0.49
     bodem
    -0.49
    Pratique
    -0.49
    POSITIVE LOGITS
    ties
    0.85
     nice
    0.82
     neat
    0.78
     touches
    0.74
     smelling
    0.73
     touch
    0.72
    NICE
    0.72
     little
    0.72
     TOUCH
    0.72
     tidy
    0.70
    Activations Density 0.057%

    No Known Activations