© 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. 16-GEMMASCOPE-RES-16K
    11. 1223
    Prev
    Next
    INDEX
    Explanations

    data and analyses related to gene expression and quantification

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

    "experiments" or data representation

    np_acts-logits-general · gemini-2.0-flash

    data represent experiments were conducted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الإنجليزية
    -0.46
    oday
    -0.43
    Jereo
    -0.40
     traditional
    -0.38
     prophets
    -0.36
    ...
    -0.35
     يتيمه
    -0.35
     bed
    -0.34
    نی
    -0.34
     poko
    -0.34
    POSITIVE LOGITS
     nahilalakip
    0.98
     triplicate
    0.88
    AnchorStyles
    0.84
     &___
    0.84
     reproducibility
    0.83
     Roskov
    0.80
    addContainerGap
    0.78
     getItemCount
    0.77
     ModelExpression
    0.76
    EndInit
    0.75
    Activations Density 1.498%

    No Known Activations