© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8822
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to dialogue and community discussions on sensitive societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    非常的
    -0.61
     being
    -0.59
    很多的
    -0.59
     there
    -0.57
    慢慢的
    -0.55
     '
    -0.52
    Datuak
    -0.52
    Whilst
    -0.51
     ‘
    -0.50
     etc
    -0.50
    POSITIVE LOGITS
     pleaſure
    1.04
    脚注の使い方
    1.03
     Majefty
    0.97
    ſelf
    0.94
     itſelf
    0.93
     purpoſe
    0.91
     myſelf
    0.90
     houſe
    0.89
     poffible
    0.88
     Jefus
    0.84
    Activations Density 1.028%

    No Known Activations