© 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. 21-GEMMASCOPE-RES-16K
    11. 3453
    Prev
    Next
    INDEX
    Explanations

    references to comparisons or contrasts between entities

    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
     các
    -0.57
    abundance
    -0.51
     cœurs
    -0.49
     âmes
    -0.46
     standpoint
    -0.42
     váš
    -0.42
    medy
    -0.41
    ulada
    -0.41
    algorithm
    -0.41
     genoux
    -0.41
    POSITIVE LOGITS
     виправивши
    0.93
     headphones
    0.88
     wireType
    0.88
     initials
    0.87
     credentials
    0.85
     stairs
    0.84
     instructions
    0.82
     lyrics
    0.82
     ***!
    0.81
     surroundings
    0.81
    Activations Density 0.490%

    No Known Activations