© 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-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 12990
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships, particularly involving the concept of a husband

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.82
     transférez
    -0.64
    IVEREF
    -0.64
    僕も
    -0.63
    俺は
    -0.63
    俺
    -0.62
     noDo
    -0.62
    DockStyle
    -0.59
     snippetHide
    -0.59
     للمعارف
    -0.58
    POSITIVE LOGITS
    Obrigada
    0.66
    ค่ะ
    0.64
    นะคะ
    0.49
     désol
    0.48
    คะ
    0.47
     suami
    0.45
     suaminya
    0.40
    いらっしゃ
    0.40
     thoughtfully
    0.40
    łam
    0.39
    Activations Density 0.746%

    No Known Activations