© 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-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 9331
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to reversal and inversion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.44
    loaf
    -0.41
     suficientemente
    -0.40
    rinfo
    -0.40
    ompok
    -0.40
    chymal
    -0.40
    ooplankton
    -0.39
    SIZ
    -0.39
    prüche
    -0.39
     Toko
    -0.39
    POSITIVE LOGITS
     reverse
    1.50
     Reverse
    1.36
     reversed
    1.34
    reverse
    1.30
    Reverse
    1.28
     reverses
    1.19
     reversing
    1.15
    reversed
    1.13
     inverse
    1.12
     reversal
    1.12
    Activations Density 0.158%

    No Known Activations