© 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. 4320
    Prev
    Next
    INDEX
    Explanations

    references to specific databases or tools used in cancer genomics

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

    Abbreviations immediately before "AD"

    np_acts-logits-general · gemini-2.0-flash

    SN, NSC, CSP, LSM abbreviations

    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
    Története
    -0.67
     bie
    -0.62
    hagic
    -0.60
    fromCharCode
    -0.60
    ểu
    -0.58
     Unido
    -0.58
    ontent
    -0.58
    forcement
    -0.57
    oltán
    -0.56
     merke
    -0.54
    POSITIVE LOGITS
     jScrollPane
    1.05
     tsk
    0.79
     Esco
    0.77
     NSM
    0.77
     للاسماء
    0.75
     AssemblyVersion
    0.74
     onPostExecute
    0.72
    Personensuche
    0.71
    JvmStatic
    0.70
     CSE
    0.69
    Activations Density 0.662%

    No Known Activations