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. 13-GEMMASCOPE-RES-16K
    6. 20
    Prev
    Next
    INDEX
    Explanations

    references to the geographical term "North" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to geographic locations, especially those related to "North" regions.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Krakowie
    -0.88
    sstream
    -0.88
    formik
    -0.85
     ModelRenderer
    -0.85
    LEncoder
    -0.85
    marvin
    -0.84
    %">
    -0.82
    })*/
    -0.80
     Pacer
    -0.78
    GEBURTSDATUM
    -0.78
    POSITIVE LOGITS
     North
    1.49
    north
    1.46
    North
    1.35
    NORTH
    1.28
     north
    1.28
     NORTH
    1.24
     Noth
    1.15
     Nort
    1.06
     East
    1.03
     South
    0.98
    Activations Density 0.063%

    No Known Activations