© 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. 18-GEMMASCOPE-RES-16K
    11. 64
    Prev
    Next
    INDEX
    Explanations

    content related to gender roles and decision-making dynamics within relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "the"

    np_acts-logits-general · gemini-2.0-flash

    majority of work and decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -1.05
    SharedCtor
    -1.05
    aarrggbb
    -0.97
    __":
    -0.93
     kasarigan
    -0.92
     MainAxisSize
    -0.88
    ViewFeatures
    -0.85
    __':
    -0.79
    CppMethod
    -0.79
    djangoproject
    -0.79
    POSITIVE LOGITS
     most
    0.66
    most
    0.60
     the
    0.60
     majority
    0.57
     большинство
    0.53
     primary
    0.53
    init
    0.53
     meeste
    0.51
     большин
    0.49
     majorité
    0.49
    Activations Density 0.355%

    No Known Activations