© 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. 7-GEMMASCOPE-RES-16K
    11. 15939
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases associated with cell adhesion and related biological processes

    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
    IsContent
    -0.90
     المعيارى
    -0.88
    ValueStyle
    -0.82
     Anſ
    -0.78
    tagHelperRunner
    -0.76
    ContentAsync
    -0.74
     ſche
    -0.72
     Monfieur
    -0.72
     AssemblyCompany
    -0.72
     censiti
    -0.72
    POSITIVE LOGITS
     receptors
    0.45
     driven
    0.45
    itzende
    0.45
    tokine
    0.45
    Morfologia
    0.44
     topped
    0.43
    upol
    0.42
    /
    0.42
    нки
    0.42
     Parker
    0.42
    Activations Density 2.075%

    No Known Activations