© 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. 11-GEMMASCOPE-RES-16K
    11. 14481
    Prev
    Next
    INDEX
    Explanations

    positive attributes and commendations related to people, particularly their talents and character traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jenner
    -0.59
    migrationBuilder
    -0.55
    findpost
    -0.53
    rolment
    -0.53
    หน่อย
    -0.53
    RenderAtEndOf
    -0.53
    fVar
    -0.53
    urlopen
    -0.52
    sprü
    -0.52
    }{%
    -0.51
    POSITIVE LOGITS
     talent
    0.79
     talents
    0.77
     talento
    0.73
     talentos
    0.68
     talented
    0.66
     gifted
    0.65
    unmodifiable
    0.64
    XmlAccessType
    0.61
     outstanding
    0.60
     extraordinary
    0.59
    Activations Density 0.201%

    No Known Activations