© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4724
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hypothetical or conditional situations involving generational reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seamnă
    -0.49
    zös
    -0.45
    jenost
    -0.43
     cứ
    -0.43
     préc
    -0.42
    ResponseWriter
    -0.42
    前期
    -0.41
    挽
    -0.41
     completely
    -0.40
    SourceChecksum
    -0.40
    POSITIVE LOGITS
    Personensuche
    0.99
     AssemblyCompany
    0.73
     Approve
    0.72
    Tikang
    0.67
    MemoryWarning
    0.65
    godic
    0.65
     approves
    0.63
     approving
    0.62
     approve
    0.61
    XmlAccessType
    0.61
    Activations Density 0.170%

    No Known Activations