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. 14-GEMMASCOPE-RES-16K
    6. 2769
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.53
     poupée
    -0.52
     chậm
    -0.50
     giai
    -0.50
     escapar
    -0.49
     köt
    -0.49
     Vorbild
    -0.48
     mourut
    -0.48
    ">//
    -0.48
    creva
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.88
     previous
    0.85
    previous
    0.78
     Previous
    0.75
     familiar
    0.75
     usual
    0.74
     previously
    0.71
    basicConfig
    0.70
    普段
    0.70
    Previous
    0.68
    Activations Density 0.377%

    No Known Activations