© 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. 10456
    Prev
    Next
    INDEX
    Explanations

    statements indicating false conditions or invalid scenarios

    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
     وتسجيلات
    -0.82
    زیین
    -0.74
     EClass
    -0.72
    getch
    -0.72
     سكانية
    -0.70
    olingo
    -0.69
     Magi
    -0.69
    brainly
    -0.68
     essenciais
    -0.68
    зулта
    -0.68
    POSITIVE LOGITS
     false
    2.14
    false
    1.99
     False
    1.84
    False
    1.76
     FALSE
    1.53
    FALSE
    1.45
     falsely
    1.40
     fals
    1.30
     falsa
    1.26
     falso
    1.26
    Activations Density 0.111%

    No Known Activations