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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9647
    Prev
    Next
    INDEX
    Explanations

    contact information and numerical data related to people and businesses

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

    preceding numbers

    np_acts-logits-general · gemini-2.0-flash

    bigg, explain, there

    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
    Rhestr
    -1.14
     مشين
    -1.03
    onViewCreated
    -0.97
    RegressionTest
    -0.95
    ValueStyle
    -0.93
     disambiguazione
    -0.93
    IsContent
    -0.91
    SharedDtor
    -0.90
    новниш
    -0.88
    Personensuche
    -0.87
    POSITIVE LOGITS
     
    0.56
     generally
    0.46
    -
    0.45
    Pro
    0.44
     near
    0.43
     true
    0.42
    pro
    0.41
    /
    0.41
     Pro
    0.41
    ou
    0.40
    Activations Density 0.029%

    No Known Activations