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. 17-GEMMASCOPE-RES-16K
    6. 6010
    Prev
    Next
    INDEX
    Explanations

    phrases related to birth or the act of being born

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Shady
    -0.62
    appcompat
    -0.61
    Guys
    -0.60
    guys
    -0.60
     Guys
    -0.57
    stüt
    -0.56
    ionage
    -0.56
    tti
    -0.54
    Xie
    -0.53
    usias
    -0.51
    POSITIVE LOGITS
     birth
    0.91
     BORN
    0.90
    ंदीखरीदारी
    0.80
     Reborn
    0.79
     Birth
    0.77
     born
    0.76
     reborn
    0.76
     Rebirth
    0.76
     BIRTH
    0.75
    featureID
    0.75
    Activations Density 0.103%

    No Known Activations