© 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. 20-GEMMASCOPE-RES-16K
    11. 13161
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to project management and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a conditional "if"

    np_acts-logits-general · gemini-2.0-flash

    if X is Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     probably
    -0.94
    probably
    -0.93
    Probably
    -0.88
    may
    -0.87
     Probably
    -0.84
     sicherlich
    -0.81
     sicuramente
    -0.77
     may
    -0.77
     prolly
    -0.76
     tentu
    -0.73
    POSITIVE LOGITS
     fails
    0.89
     forem
    0.76
     fizer
    0.71
     were
    0.71
     yoksa
    0.70
     becomes
    0.69
     exceeds
    0.69
     decides
    0.68
     happens
    0.68
     tiver
    0.67
    Activations Density 0.688%

    No Known Activations