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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 5231
    Prev
    Next
    INDEX
    Explanations

    terms related to specific geographical locations and communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scriptcase
    -0.59
     Enugu
    -0.56
     django
    -0.55
    siella
    -0.51
     Pune
    -0.51
     Telugu
    -0.48
     Warwickshire
    -0.48
     elegans
    -0.47
    佗
    -0.47
    gige
    -0.47
    POSITIVE LOGITS
     Arctic
    1.28
     arctic
    1.22
    Arctic
    1.15
     Alaska
    1.05
    arctic
    1.05
     Alaskan
    1.04
     Greenland
    1.03
     tundra
    1.03
     reindeer
    0.98
    Alaska
    0.97
    Activations Density 0.242%

    No Known Activations