© 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. 10462
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate comparisons or ratios

    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
     pendiente
    -0.70
    children
    -0.67
    pend
    -0.65
     Zust
    -0.64
     Eme
    -0.64
    estrian
    -0.64
     Children
    -0.62
     bint
    -0.61
     TSS
    -0.61
    Eme
    -0.61
    POSITIVE LOGITS
     Ratios
    1.17
     ratios
    1.14
     CURIAM
    1.03
     RATIO
    0.97
    ratios
    0.97
     Segura
    0.95
     Sura
    0.94
    djangoproject
    0.93
     Balboa
    0.92
     Ratio
    0.92
    Activations Density 0.122%

    No Known Activations