Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 11897
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their roles within government

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rass
    -0.84
    ActivityCompat
    -0.78
     Oxy
    -0.74
     Hå
    -0.72
    %)$
    -0.72
     Gracie
    -0.68
     XY
    -0.67
     Grimal
    -0.66
     Smack
    -0.66
     Braw
    -0.66
    POSITIVE LOGITS
     ministers
    1.96
     minister
    1.78
     Ministers
    1.75
     Minister
    1.73
     MINISTER
    1.61
    Minister
    1.59
    minister
    1.48
     ministries
    1.28
     ministerial
    1.21
     ministry
    1.14
    Activations Density 0.069%

    No Known Activations