© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4485
    Prev
    Next
    INDEX
    Explanations

    absence of relevant content or information in the text

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

    Followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    Your Car, Nowadays, type, 2, Relevance, 1

    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
     Мексичка
    -0.82
     autorytatywna
    -0.74
    setViewName
    -0.71
     EnglishChoose
    -0.71
    Autoritní
    -0.70
    Παραπομπές
    -0.68
    NUMX
    -0.67
    bootstrapcdn
    -0.67
    DataSnapshot
    -0.66
    Enllaces
    -0.66
    POSITIVE LOGITS
    ↵↵
    1.61
    ↵↵↵
    1.06
    ↵
    0.82
    ↵↵↵↵
    0.78
    ↵↵↵↵↵
    0.75
    <eos>
    0.74
    ↵↵↵↵↵↵
    0.64
    ↵↵↵↵↵↵↵
    0.59
     Also
    0.59
     sherds
    0.57
    Activations Density 0.085%

    No Known Activations