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. 4-GEMMASCOPE-RES-16K
    6. 15926
    Prev
    Next
    INDEX
    Explanations

    references to actions and commands involving "we," "I," and forms of "to let."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextAppearance
    -0.53
     HttpResponse
    -0.52
     aidant
    -0.51
     connexe
    -0.50
    lah
    -0.49
     Rine
    -0.47
    OGND
    -0.47
    LabelTagHelper
    -0.46
     boîte
    -0.45
    LElement
    -0.44
    POSITIVE LOGITS
    Теперь
    0.74
     continúas
    0.71
     Теперь
    0.71
    ValueStyle
    0.70
     autorytatywna
    0.69
    adaptiveStyles
    0.67
    ViewFeatures
    0.67
    RTSC
    0.65
    הערות
    0.64
    Maintenant
    0.63
    Activations Density 0.185%

    No Known Activations