© 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. 16022
    Prev
    Next
    INDEX
    Explanations

    references to mountains and hilly landscapes

    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
     DELHI
    -0.79
    irical
    -0.72
    CHICAGO
    -0.69
    vieja
    -0.69
     Qantas
    -0.67
     CHICAGO
    -0.66
    çais
    -0.64
     sanitarios
    -0.64
     hefyd
    -0.64
    fredo
    -0.63
    POSITIVE LOGITS
     hills
    1.55
     mountain
    1.48
     mountains
    1.46
     hill
    1.41
     Mountain
    1.37
    Mountain
    1.27
     Hills
    1.24
     Mountains
    1.21
     Hill
    1.21
    mountain
    1.17
    Activations Density 0.120%

    No Known Activations