Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4381
    Prev
    Next
    INDEX
    Explanations

    phrases that describe creative processes and artistic elements

    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
    ʺ
    -0.49
     illi
    -0.39
     ï
    -0.39
    ⁢
    -0.39
     ་་
    -0.39
    ruik
    -0.38
     ब्रेकडाउन
    -0.38
     diu
    -0.38
    ÉT
    -0.38
     corne
    -0.37
    POSITIVE LOGITS
     ancaman
    0.81
     semacam
    0.80
     quizá
    0.80
     keduanya
    0.79
     setidaknya
    0.78
     rumahnya
    0.77
     venganza
    0.75
     conmigo
    0.74
     quizás
    0.74
     sesuatu
    0.73
    Activations Density 11.479%

    No Known Activations