© 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. 6906
    Prev
    Next
    INDEX
    Explanations

    financial terms and support-related phrases

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

    Belgian or Flemish contexts

    np_acts-logits-general · gemini-2.0-flash

    Belgian and associated places

    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
    مرار
    -0.48
     ejus
    -0.48
    toThrow
    -0.48
     Anf
    -0.47
     Sydney
    -0.46
     Skye
    -0.46
     cil
    -0.46
     scissor
    -0.46
     sydney
    -0.45
    Skye
    -0.45
    POSITIVE LOGITS
     Belgian
    1.26
     Belgium
    1.20
    Belgian
    1.18
    Belgium
    1.12
     Flemish
    1.08
     Belgi
    1.08
     Bélgica
    0.97
     belga
    0.97
     Brussels
    0.94
     belg
    0.92
    Activations Density 0.137%

    No Known Activations