© 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. 15-GEMMASCOPE-RES-16K
    11. 1172
    Prev
    Next
    INDEX
    Explanations

    instances of gaps or discrepancies in information or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reverso
    -0.58
    estina
    -0.55
    zeb
    -0.55
     MwSt
    -0.51
    maketitle
    -0.50
    anyahu
    -0.49
    GeneratedCode
    -0.49
    はじめに
    -0.49
     strtolower
    -0.47
    buah
    -0.47
    POSITIVE LOGITS
     gap
    1.17
     gaps
    1.09
     Gap
    1.07
     Gaps
    1.05
    Gap
    1.04
    gap
    1.02
     between
    0.98
     GAP
    0.84
    gaps
    0.82
     BETWEEN
    0.80
    Activations Density 0.508%

    No Known Activations