© 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. 11-GEMMASCOPE-RES-16K
    11. 1672
    Prev
    Next
    INDEX
    Explanations

    specific terms related to data subsets and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.03
     Efq
    -1.01
     Theſe
    -0.89
    IsContent
    -0.89
     whoſe
    -0.85
     ſeveral
    -0.82
     Houſe
    -0.81
     myſelf
    -0.81
     itſelf
    -0.79
     houſe
    -0.79
    POSITIVE LOGITS
    BeginContext
    0.56
    jstor
    0.53
     *
    0.51
     invokevirtual
    0.49
     اكتوبر
    0.47
    DECREF
    0.47
     OMITBAD
    0.45
    /
    0.44
     per
    0.43
    الإنجليزية
    0.41
    Activations Density 1.219%

    No Known Activations