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. 18-GEMMASCOPE-RES-16K
    6. 8371
    Prev
    Next
    INDEX
    Explanations

    names and attributes related to individuals in a narrative context

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

    West African locations

    np_acts-logits-general · gemini-2.0-flash

    West African countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.69
    usercontent
    -0.61
     Eileen
    -0.53
    ObjectContext
    -0.51
    esModule
    -0.50
     Abia
    -0.48
    localctx
    -0.48
    poca
    -0.47
     lưu
    -0.47
     انج
    -0.47
    POSITIVE LOGITS
     Senegal
    0.96
     Gambia
    0.93
     Sene
    0.87
    Senegal
    0.87
     Sénégal
    0.83
     Dakar
    0.65
    énégal
    0.62
     sene
    0.61
     Sén
    0.59
     sén
    0.58
    Activations Density 0.095%

    No Known Activations