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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11873
    Prev
    Next
    INDEX
    Explanations

    Arabic words and names, particularly those related to Islamic culture and literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleType
    -0.86
     المعيارى
    -0.66
    ViewFeatures
    -0.60
    Revenir
    -0.56
     reap
    -0.56
     خارجية
    -0.53
     zvuky
    -0.53
    ruptedException
    -0.52
    openqa
    -0.52
     anti
    -0.52
    POSITIVE LOGITS
     itſelf
    0.85
    thâu
    0.77
    InjectAttribute
    0.69
     himſelf
    0.69
     auroit
    0.67
     themſelves
    0.66
     feroit
    0.66
     Houſe
    0.63
     enfans
    0.63
     Hn
    0.62
    Activations Density 0.537%

    No Known Activations