© 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. 9762
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and expressions of appreciation

    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
     незавершена
    -0.89
    @[+][
    -0.73
     Normdatei
    -0.73
     ویکی‌پدیا
    -0.70
    Geplaatst
    -0.65
    Kjelder
    -0.63
    verifyException
    -0.61
     виправивши
    -0.61
     orina
    -0.60
     Referenzen
    -0.59
    POSITIVE LOGITS
     تانيه
    0.51
    αρα
    0.48
     sorry
    0.47
    Tis
    0.44
     transfieras
    0.43
     mans
    0.43
    pter
    0.42
     simple
    0.42
    scalatest
    0.41
     morning
    0.41
    Activations Density 0.142%

    No Known Activations