Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 6211
    Prev
    Next
    INDEX
    Explanations

    emotional restraint and control in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igli
    -0.57
    LM
    -0.54
    ‚¬
    -0.53
     either
    -0.52
    k
    -0.52
     Bamb
    -0.51
    вр
    -0.50
    َي
    -0.49
    ach
    -0.47
     do
    -0.47
    POSITIVE LOGITS
     myſelf
    1.03
     photolibrary
    0.99
     itſelf
    0.96
     restraint
    0.94
     suppressed
    0.93
     suppresses
    0.93
     Houſe
    0.90
     suppressing
    0.90
     againſt
    0.88
     Majefty
    0.87
    Activations Density 0.295%

    No Known Activations