© 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. 7-GEMMASCOPE-RES-16K
    11. 9888
    Prev
    Next
    INDEX
    Explanations

    references to duality or comparisons between two entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allemaal
    -0.72
     houſe
    -0.71
     Efq
    -0.70
    ſelf
    -0.68
    ształ
    -0.67
     وتسجيلات
    -0.67
     ſeveral
    -0.67
     wireType
    -0.67
     ſtate
    -0.66
     purpoſe
    -0.66
    POSITIVE LOGITS
     two
    1.09
     Two
    1.05
     beiden
    1.03
    two
    0.98
     Both
    0.97
    Two
    0.96
    Both
    0.95
     duo
    0.94
     deux
    0.92
     Beide
    0.90
    Activations Density 1.471%

    No Known Activations