© 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. 15-GEMMASCOPE-RES-16K
    11. 1741
    Prev
    Next
    INDEX
    Explanations

    interactions and expressions of disbelief or surprise in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
    TypedDataSet
    -0.58
     pungkas
    -0.54
    Билгалдахарш
    -0.53
    Geplaatst
    -0.51
     beginnetje
    -0.50
    tamment
    -0.50
    sidemargin
    -0.49
     оригіналу
    -0.46
     initComponents
    -0.46
    دانشنامهٔ
    -0.45
    POSITIVE LOGITS
    AddHtmlAttribute
    0.40
    RegressionTest
    0.39
     grain
    0.35
     scrub
    0.34
     beat
    0.33
     tro
    0.33
     rep
    0.32
    ########.
    0.32
     rush
    0.32
     rough
    0.32
    Activations Density 0.096%

    No Known Activations