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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 102507
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to women in waiting or service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     facie
    -0.44
     newData
    -0.44
    tonode
    -0.44
    ]")]
    -0.44
    setHorizontal
    -0.43
    awaiter
    -0.43
    rotter
    -0.43
    vez
    -0.41
    indelijk
    -0.41
    ParallelGroup
    -0.41
    POSITIVE LOGITS
     bridesmaid
    0.76
     bridesmaids
    0.70
    PMailer
    0.53
    олові
    0.51
     teammates
    0.48
     Brides
    0.47
    maids
    0.46
     teammate
    0.43
     marié
    0.43
     invitados
    0.43
    Activations Density 0.002%

    No Known Activations