© 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. 7799
    Prev
    Next
    INDEX
    Explanations

    technical processes and specific methods related to molecular biology experiments

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

    "Copy" or "paste" actions

    np_acts-logits-general · gemini-2.0-flash

    copy and paste actions

    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
     دیکھیے
    -0.49
     amma
    -0.49
     baku
    -0.47
    irls
    -0.47
    WebVitals
    -0.46
    ReadKey
    -0.46
    ivar
    -0.46
    kerne
    -0.46
    케
    -0.45
    )++;
    -0.45
    POSITIVE LOGITS
     pasting
    1.11
     clipboard
    1.09
     paste
    1.03
    paste
    0.98
     Paste
    0.98
     pasted
    0.95
    Paste
    0.94
     Clipboard
    0.94
    Clipboard
    0.89
     copied
    0.89
    Activations Density 0.399%

    No Known Activations