© 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. 14-GEMMASCOPE-RES-16K
    6. 497
    Prev
    Next
    INDEX
    Explanations

    scientific data terminology related to genetic analysis and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.50
    itek
    -0.49
     again
    -0.48
     kock
    -0.47
    again
    -0.47
    ielen
    -0.46
     Again
    -0.44
    assignment
    -0.41
    getTask
    -0.41
    ામ
    -0.41
    POSITIVE LOGITS
     surrounding
    1.01
    ViewFeatures
    0.84
     neighbouring
    0.83
     nearby
    0.81
     vicinity
    0.80
     Nearby
    0.79
     nearest
    0.76
     Nearest
    0.75
    nearby
    0.74
    Nearby
    0.71
    Activations Density 0.755%

    No Known Activations