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. 22-GEMMASCOPE-RES-16K
    6. 14104
    Prev
    Next
    INDEX
    Explanations

    references to socioeconomic conditions and geography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    DoubleQuotes
    -0.70
    ISupport
    -0.59
    }>;
    -0.57
    spm
    -0.56
     CiNii
    -0.54
     Verfahrens
    -0.52
    stdc
    -0.51
     '{@
    -0.51
    spitze
    -0.51
     gider
    -0.51
    POSITIVE LOGITS
     communities
    0.90
     underserved
    0.75
     cities
    0.74
     comunidades
    0.67
    communities
    0.67
     jurisdictions
    0.65
    Personensuche
    0.64
     municipalities
    0.64
     disadvantaged
    0.63
     regions
    0.62
    Activations Density 0.335%

    No Known Activations