© 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. 13113
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional or hypothetical statements

    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
    ScopeManager
    -0.67
     Bildern
    -0.66
    trägen
    -0.66
     Punkten
    -0.65
    someone
    -0.64
     Städten
    -0.64
     someone
    -0.64
     Produkten
    -0.64
     Preisen
    -0.63
     Geräten
    -0.61
    POSITIVE LOGITS
     those
    0.50
    Those
    0.47
    över
    0.47
     zvuky
    0.45
    வை
    0.45
     typy
    0.45
     Those
    0.44
     проекты
    0.44
    那些
    0.44
     projekty
    0.43
    Activations Density 0.029%

    No Known Activations