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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8027
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or involvement of women in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.94
     pleaſure
    -0.89
     juſ
    -0.81
     ſever
    -0.80
     myſelf
    -0.79
     feroit
    -0.77
     uſe
    -0.77
     ſtate
    -0.77
     uſed
    -0.75
     ſta
    -0.74
    POSITIVE LOGITS
    s
    1.37
     s
    0.69
    {~
    0.60
     own
    0.59
    𝑠
    0.55
    ils
    0.54
    Ys
    0.52
    etts
    0.52
    mens
    0.52
    ds
    0.51
    Activations Density 0.248%

    No Known Activations