© 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. 640
    Prev
    Next
    INDEX
    Explanations

    references to prior actions or conditions related to decision making or legal processes

    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
     Majefty
    -0.60
    bootstrapcdn
    -0.56
    toggler
    -0.54
     uiteindelijk
    -0.53
    __["
    -0.53
    ">:
    -0.53
     Enti
    -0.53
     congi
    -0.53
    Migration
    -0.52
    addContainerGap
    -0.52
    POSITIVE LOGITS
     виправивши
    0.77
     Antes
    0.71
     antes
    0.70
     had
    0.69
     vorher
    0.67
     فريبيس
    0.66
    Antes
    0.66
     sempat
    0.64
     terlebih
    0.63
     sebelumnya
    0.63
    Activations Density 0.166%

    No Known Activations