© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 8337
    Prev
    Next
    INDEX
    Explanations

    instances of the word "take" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.57
    MessageTagHelper
    -0.54
     typelib
    -0.51
    isContained
    -0.50
     ModelExpression
    -0.50
    uxxxx
    -0.50
    MLLoader
    -0.49
    EndGlobalSection
    -0.49
    webElementXpaths
    -0.48
     vermelhas
    -0.47
    POSITIVE LOGITS
     advantage
    1.20
     care
    0.92
    advantage
    0.82
     charge
    0.69
     avantage
    0.65
     note
    0.65
     part
    0.65
     pleaſure
    0.64
     Advantage
    0.62
     possession
    0.59
    Activations Density 0.103%

    No Known Activations