© 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. 23-GEMMASCOPE-RES-16K
    11. 9285
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographic locations and associated entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     keting
    -0.53
     Seas
    -0.51
     Océ
    -0.51
     Seaside
    -0.51
     Ocean
    -0.50
    Ocean
    -0.49
     seaside
    -0.48
     gyhoeddwyd
    -0.48
     ondu
    -0.47
     Oce
    -0.47
    POSITIVE LOGITS
     channel
    0.84
    ThroughAttribute
    0.75
     anchorage
    0.71
    channel
    0.71
     ModelExpression
    0.70
     entrance
    0.68
     CHANNEL
    0.68
     mouth
    0.67
     channels
    0.67
    出版年
    0.66
    Activations Density 0.231%

    No Known Activations