© 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. 10-GEMMASCOPE-RES-16K
    11. 10534
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.74
    certainly
    -0.62
     certainly
    -0.62
    ınd
    -0.60
     @}
    -0.59
    oges
    -0.58
     also
    -0.58
    SOUNDBITE
    -0.57
     zwar
    -0.56
     également
    -0.56
    POSITIVE LOGITS
     Просто
    0.91
     Simplemente
    0.81
    Просто
    0.80
     egyszerű
    0.77
     simply
    0.76
     незавершена
    0.74
     simplesmente
    0.72
    Simply
    0.71
     plain
    0.70
    simply
    0.69
    Activations Density 0.241%

    No Known Activations