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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 4118
    Prev
    Next
    INDEX
    Explanations

    technical language related to inventions and manufacturing processes

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

    Follows punctuation and transitional words

    np_acts-logits-general · gemini-2.0-flash

    conjunctions after description

    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
    —
    -0.45
     
    -0.40
     —
    -0.40
      
    -0.39
    ,
    -0.38
    :
    -0.38
    块钱
    -0.38
    â
    -0.37
     –
    -0.37
     du
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    0.95
     Jpn
    0.90
    脚注の使い方
    0.89
    новниш
    0.88
     CiNii
    0.87
    참고
    0.84
     NDL
    0.83
    WebVitals
    0.82
     ſever
    0.81
     незавершена
    0.81
    Activations Density 2.452%

    No Known Activations