© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 432
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "convert" along with associated terms indicating transformation or change

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

    Transformation or changing formats

    np_acts-logits-general · gemini-2.0-flash

    converting from one form to another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.63
    ague
    -0.54
    RUnlock
    -0.54
     IndexError
    -0.53
    lastIndexOf
    -0.52
    ignement
    -0.52
    boutin
    -0.52
     ब्रेकडाउन
    -0.50
    contentPadding
    -0.50
    Bandwidth
    -0.50
    POSITIVE LOGITS
     convert
    1.02
     transforms
    0.97
     conversion
    0.95
     converts
    0.95
     transform
    0.93
     transformation
    0.93
     converted
    0.93
     Convert
    0.93
     transformed
    0.91
     converting
    0.90
    Activations Density 0.198%

    No Known Activations