Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 10778
    Prev
    Next
    INDEX
    Explanations

    expressions of moral judgment regarding actions and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.79
    IntoConstraints
    -0.78
    parsedMessage
    -0.75
     متعلقه
    -0.75
    webElementXpaths
    -0.74
    ValueStyle
    -0.73
     utafitiHapana
    -0.72
    ódó
    -0.71
    хьтан
    -0.69
     виправивши
    -0.68
    POSITIVE LOGITS
     people
    0.79
     sometimes
    0.66
     stereotypes
    0.65
     stereotype
    0.64
    people
    0.60
     ignorant
    0.59
    有些人
    0.59
     often
    0.59
     misunderstand
    0.57
     Often
    0.57
    Activations Density 0.799%

    No Known Activations