© 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. 3040
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specificity or uncertainty

    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
     hydro
    -0.53
     hydropower
    -0.52
    libatkan
    -0.52
     Grüsse
    -0.51
     compres
    -0.51
     Gown
    -0.51
     liquef
    -0.50
     hyd
    -0.50
    wakili
    -0.50
    Grüsse
    -0.49
    POSITIVE LOGITS
     certain
    1.19
     Certain
    1.18
    Certain
    1.15
    certain
    1.11
     CERTAIN
    1.00
     certaine
    0.85
     ciertos
    0.83
     ciertas
    0.81
     tertentu
    0.80
     cierto
    0.78
    Activations Density 0.123%

    No Known Activations