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. 2684
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory terms and procedures

    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
     equally
    -0.55
     guarn
    -0.47
     or
    -0.46
    …
    -0.46
     memu
    -0.46
    age
    -0.45
     budget
    -0.43
     đảo
    -0.43
    </strong>
    -0.43
     where
    -0.42
    POSITIVE LOGITS
     Meksiku
    0.91
    Gambas
    0.83
    thâu
    0.79
     Савезне
    0.77
     kasarigan
    0.74
     betweenstory
    0.74
    UserScript
    0.70
     '\\;'
    0.70
    InjectAttribute
    0.70
     ligiloj
    0.70
    Activations Density 0.658%

    No Known Activations