© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8245
    Prev
    Next
    INDEX
    Explanations

    instances of the word "utils" and variations thereof, typically in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rød
    -0.62
     quæ
    -0.58
     AppCompat
    -0.57
    pendente
    -0.57
     sauvages
    -0.56
     panahon
    -0.55
     soprav
    -0.55
     vandens
    -0.54
     foncé
    -0.52
     accord
    -0.52
    POSITIVE LOGITS
    encodeWith
    0.72
     propOrder
    0.72
     незавершена
    0.65
    ]$.
    0.65
    Бахар
    0.64
     wasted
    0.64
     harassment
    0.63
     streaming
    0.62
     تضيفلها
    0.61
    esía
    0.60
    Activations Density 0.111%

    No Known Activations