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. 20-GEMMASCOPE-RES-16K
    6. 15743
    Prev
    Next
    INDEX
    Explanations

    terms related to women and their rights

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

    Follows possessive "'s" or "’s"

    np_acts-logits-general · gemini-2.0-flash

    's followed by rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bbene
    -0.58
    tagHelperRunner
    -0.57
    évaluateur
    -0.56
    ValueStyle
    -0.54
     everyone
    -0.52
    empereur
    -0.52
     verrez
    -0.51
     myſelf
    -0.50
    Personendaten
    -0.49
     himſelf
    -0.49
    POSITIVE LOGITS
    expandindo
    0.62
    HideFlags
    0.57
     Rights
    0.57
    AddTagHelper
    0.57
     '\\;'
    0.56
    HomeAsUpEnabled
    0.53
    дём
    0.53
    MigrationBuilder
    0.53
     rights
    0.53
    itní
    0.52
    Activations Density 0.156%

    No Known Activations