© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 16255
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate changes, specific conditions, or actions, particularly in a scientific or analytical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnitTesting
    -0.66
    WillAppear
    -0.64
    SourceChecksum
    -0.63
    MemoryWarning
    -0.61
     Herod
    -0.60
    SpringBootTest
    -0.60
    ungeon
    -0.60
    GraphicsUnit
    -0.59
     presided
    -0.58
     Perſ
    -0.58
    POSITIVE LOGITS
     weiteren
    0.53
     further
    0.52
     futuros
    0.50
     futuras
    0.49
     weiterer
    0.48
     ytterligare
    0.48
     future
    0.47
     being
    0.47
     prochain
    0.47
     المزيد
    0.47
    Activations Density 0.229%

    No Known Activations