© 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. 5837
    Prev
    Next
    INDEX
    Explanations

    technical jargon or terminology related to data processing

    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
    endphp
    -0.88
    Slf
    -0.80
    ########.
    -0.77
    stdc
    -0.74
    MemoryWarning
    -0.74
    RectangleBorder
    -0.71
    tableFuture
    -0.70
    endforeach
    -0.69
    ChildScrollView
    -0.69
    MONG
    -0.68
    POSITIVE LOGITS
    XtraEditors
    1.04
     DevExpress
    0.97
    XtraGrid
    0.68
     inalámbrico
    0.61
     היתה
    0.54
    HeaderText
    0.54
    ⓘ
    0.52
    Xtra
    0.52
     actuels
    0.51
     vizsg
    0.51
    Activations Density 0.026%

    No Known Activations