© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1494
    Prev
    Next
    INDEX
    Explanations

    names and identities of individuals and their relationships to contexts or events

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

    West African names and places

    np_acts-logits-general · gemini-2.0-flash

    Senegalese and Gambian names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.67
    aurait
    -0.55
     havaianas
    -0.54
     Ră
    -0.54
    rawDesc
    -0.54
     nuvem
    -0.54
    mybatisplus
    -0.53
     Pipes
    -0.51
     ruines
    -0.50
    hésite
    -0.49
    POSITIVE LOGITS
     Gamb
    0.72
     Amad
    0.70
     Gambia
    0.69
     Ous
    0.66
     Adama
    0.65
    Gamb
    0.62
     Diallo
    0.62
    Lamin
    0.61
     Koro
    0.60
    junta
    0.58
    Activations Density 0.093%

    No Known Activations