© 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. 4-GEMMASCOPE-RES-16K
    11. 10585
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brainly
    -0.57
     avanti
    -0.53
    rebbero
    -0.50
    tése
    -0.49
    BoxLayout
    -0.47
    _"+
    -0.46
    reibt
    -0.45
     främ
    -0.45
     rép
    -0.45
     APIs
    -0.44
    POSITIVE LOGITS
    UserScript
    0.93
     مشين
    0.90
     kasarigan
    0.87
     resourceCulture
    0.87
    存于互联网档案馆
    0.83
    ंदीखरीदारी
    0.79
    richTextPanel
    0.77
     BoxFit
    0.77
    scriptcase
    0.75
    WriteTagHelper
    0.73
    Activations Density 0.079%

    No Known Activations