© 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. 0-GEMMASCOPE-RES-16K
    11. 8322
    Prev
    Next
    INDEX
    Explanations

    instances of the word "take" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.80
    InitVars
    -0.76
    CloseOperation
    -0.73
    ^(@)
    -0.68
     betweenstory
    -0.67
    DockStyle
    -0.67
    الحياه
    -0.66
    MetaObject
    -0.65
    gebob
    -0.65
    Története
    -0.64
    POSITIVE LOGITS
    take
    3.80
     take
    3.79
    Take
    3.58
     Take
    3.52
     takes
    3.36
    taking
    3.35
     taking
    3.33
     TAKE
    3.23
    Taking
    3.20
    takes
    3.20
    Activations Density 0.063%

    No Known Activations