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. 23-GEMMASCOPE-RES-16K
    6. 12268
    Prev
    Next
    INDEX
    Explanations

    mentions of countries and their relations to power dynamics and rights issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pulumi
    -0.79
     Malaysia
    -0.69
     Nigeria
    -0.66
     India
    -0.66
     Zimbabwe
    -0.65
     Kenya
    -0.65
     Indonesia
    -0.64
     Italy
    -0.63
     Uganda
    -0.62
     Ghana
    -0.62
    POSITIVE LOGITS
     largest
    0.81
     größ
    0.75
     coastline
    0.73
     population
    0.73
     Largest
    0.72
     citizens
    0.71
     finest
    0.71
     economy
    0.68
     Finest
    0.67
     airports
    0.66
    Activations Density 0.185%

    No Known Activations