© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 4946
    Prev
    Next
    INDEX
    Explanations

    themes related to social injustice and racial dynamics

    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
    更好地
    -0.76
     imidlertid
    -0.71
     به‌عنوان
    -0.68
    ‒
    -0.68
    地看着
    -0.67
    ​—
    -0.66
    —
    -0.66
     به‌
    -0.63
     Paesi
    -0.62
     dà
    -0.62
    POSITIVE LOGITS
     todays
    0.93
     alot
    0.93
     loosing
    0.91
     thier
    0.83
     whats
    0.81
     atleast
    0.79
     didalam
    0.78
     diatas
    0.76
    慢慢的
    0.76
     aprox
    0.75
    Activations Density 2.887%

    No Known Activations