© 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. 7-GEMMASCOPE-RES-16K
    6. 14319
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and academic publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikispecies
    -0.76
    SequentialGroup
    -0.75
     كومونز
    -0.74
    lujah
    -0.73
     &___
    -0.72
    idom
    -0.69
    atrième
    -0.68
     Audiodateien
    -0.66
    InvalidProtocol
    -0.65
    følgelig
    -0.64
    POSITIVE LOGITS
    Greater
    0.51
    denes
    0.50
     Greater
    0.48
    mybatisplus
    0.47
    wns
    0.46
    atiker
    0.46
    走去
    0.46
    Erreferentziak
    0.45
     поколения
    0.45
    قليم
    0.45
    Activations Density 0.919%

    No Known Activations