© 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. 6-GEMMASCOPE-RES-16K
    6. 14228
    Prev
    Next
    INDEX
    Explanations

    phrases related to synaptic activity and calcium signaling in the brain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.75
    VIAF
    -0.68
    enment
    -0.67
    +#+
    -0.62
     سكانية
    -0.61
    vaded
    -0.61
    nonatomic
    -0.60
    viewDidLoad
    -0.60
    UCKY
    -0.60
    Scroller
    -0.59
    POSITIVE LOGITS
    MarshalTo
    0.66
    <bos>
    0.63
     romaine
    0.60
     circulaire
    0.54
     referrerpolicy
    0.50
    Билгалдахарш
    0.49
    inerja
    0.47
     Tijuana
    0.46
     seksual
    0.46
     jadx
    0.45
    Activations Density 0.282%

    No Known Activations