© 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. 10-GEMMASCOPE-RES-16K
    11. 15470
    Prev
    Next
    INDEX
    Explanations

    instances of object creation and usage in programming languages

    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
    +#+#
    -0.97
    LookAnd
    -0.80
    kloped
    -0.79
    oredCriteria
    -0.74
    unhofer
    -0.70
    AddRange
    -0.69
     betweenstory
    -0.64
     doInBackground
    -0.64
     uska
    -0.63
    ніципалі
    -0.62
    POSITIVE LOGITS
     Nacionales
    0.55
     InputDecoration
    0.54
     trésor
    0.50
     recev
    0.48
     virksom
    0.47
     automatiques
    0.47
     trouvez
    0.47
     communs
    0.47
     couverts
    0.47
     externi
    0.46
    Activations Density 0.105%

    No Known Activations