© 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. 28-GEMMASCOPE-RES-16K
    11. 7675
    Prev
    Next
    INDEX
    Explanations

    instances of the word "take" and its variations, focusing on actions or decisions involving readers or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "takes" (forms of the word take)

    np_acts-logits-general · gemini-2.0-flash

    takes followed by noun or preposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.58
     reme
    -0.45
     referenties
    -0.42
     curs
    -0.37
    RuleContext
    -0.36
    __))
    -0.36
     MainAxisSize
    -0.34
     Spells
    -0.34
    MessageTagHelper
    -0.34
     الشم
    -0.34
    POSITIVE LOGITS
     place
    0.54
     EconPapers
    0.53
    adget
    0.49
    новниш
    0.48
    setupUi
    0.47
     Exactos
    0.47
     cherchés
    0.46
    takes
    0.45
     takes
    0.45
    lugar
    0.44
    Activations Density 0.058%

    No Known Activations