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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 8638
    Prev
    Next
    INDEX
    Explanations

    concepts related to parallel processing and computation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TextWatcher
    -0.51
    Database
    -0.40
     kapı
    -0.38
     veicolo
    -0.38
    {"
    -0.38
     consistently
    -0.37
    慷
    -0.37
    stoß
    -0.37
    --
    -0.36
     Meny
    -0.36
    POSITIVE LOGITS
    SBATCH
    1.33
    featureID
    0.98
    ]")]
    0.94
    fjspx
    0.94
    WaitGroup
    0.90
     المعيارى
    0.89
     صوتيه
    0.89
     بيها
    0.88
    __':
    
    0.87
     الاطلاع
    0.87
    Activations Density 0.604%

    No Known Activations