© 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. 10993
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and terms related to property accessors in code

    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
     betweenstory
    -0.81
     Италијани
    -0.81
    AsUp
    -0.81
     صوتيه
    -0.78
    mybatisplus
    -0.77
    abestanden
    -0.77
     المعيارى
    -0.77
     فريبيس
    -0.75
     utafitiHapana
    -0.75
     tartalomajánló
    -0.73
    POSITIVE LOGITS
    preventDefault
    0.60
     meurt
    0.56
     bigli
    0.52
     visitantes
    0.52
    InstanceState
    0.51
     courants
    0.51
     cuire
    0.51
     complètes
    0.50
     eccell
    0.49
     étroite
    0.49
    Activations Density 0.012%

    No Known Activations