© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 14361
    Prev
    Next
    INDEX
    Explanations

    negative sentiments and expressions of disdain towards individuals or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Бахар
    -0.76
    出版年
    -0.71
    ')):
    -0.63
    uxxxx
    -0.62
     GenerationType
    -0.59
    '])->
    -0.59
    parseLong
    -0.58
    RuleContext
    -0.57
     EconPapers
    -0.57
    "},
    -0.57
    POSITIVE LOGITS
     responsible
    0.60
     Doing
    0.58
     deserve
    0.58
     commend
    0.57
     verantwort
    0.57
    addFlags
    0.56
    Doing
    0.56
     melakukannya
    0.55
     responsáveis
    0.55
    abestanden
    0.54
    Activations Density 0.314%

    No Known Activations