© 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. 27-GEMMASCOPE-RES-16K
    11. 8820
    Prev
    Next
    INDEX
    Explanations

    expressions of capability or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.50
    WebElementEntity
    -0.50
     calab
    -0.50
    новништво
    -0.48
    tagext
    -0.47
    IsMutable
    -0.46
     ſel
    -0.45
     defStyle
    -0.45
     '\\;'
    -0.45
     autorytatywna
    -0.44
    POSITIVE LOGITS
     скажу
    0.77
     decir
    0.65
     saying
    0.63
     сказать
    0.61
     say
    0.61
     dizer
    0.55
     بگو
    0.55
     sagen
    0.54
    我说
    0.53
    saying
    0.52
    Activations Density 0.217%

    No Known Activations