© 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. 25-GEMMASCOPE-RES-16K
    11. 1565
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential outcomes and assessments of effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.75
    OGND
    -0.72
     می‌توانید
    -0.64
    ThroughAttribute
    -0.64
    >(_
    -0.57
     کردند
    -0.56
     CURIAM
    -0.56
    BagLayout
    -0.56
    Answered
    -0.55
     communiquez
    -0.55
    POSITIVE LOGITS
     be
    3.60
    be
    1.87
     Be
    1.69
     быть
    1.59
    Be
    1.59
     être
    1.49
     бути
    1.48
     BE
    1.41
     være
    1.41
     być
    1.39
    Activations Density 1.869%

    No Known Activations