© 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. 39-GEMMASCOPE-RES-16K
    11. 3732
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to scientific investigations and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.55
    ########.
    -0.55
    GEBURTSDATUM
    -0.52
    뀜
    -0.51
    rawDesc
    -0.49
    OCCURRED
    -0.47
     kaarangay
    -0.47
    Autoritní
    -0.47
    ۗ
    -0.45
    LEncoder
    -0.45
    POSITIVE LOGITS
     each
    4.47
    each
    3.58
    Each
    3.44
     Each
    3.41
     EACH
    2.94
     fiecare
    2.69
     ciascuno
    2.67
    EACH
    2.66
     chaque
    2.64
     ciasc
    2.59
    Activations Density 4.321%

    No Known Activations