© 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. 667
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and relationship dynamics

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

    Comes after a question

    np_acts-logits-general · gemini-2.0-flash

    phrasing a question

    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
     dezelve
    -0.52
     subsequently
    -0.52
    reszcie
    -0.51
     ilustracja
    -0.48
     Consejos
    -0.48
     betrek
    -0.48
     viajeros
    -0.47
     bezoekers
    -0.47
     Similarly
    -0.47
     bowiem
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.68
    +#+#
    0.66
    complexContent
    0.61
    ReusableCell
    0.60
    webElementXpaths
    0.60
    ChildScrollView
    0.57
    ########.
    0.52
    :✨
    0.51
     <<<<<<<<<<<<<<
    0.51
     stinks
    0.50
    Activations Density 0.410%

    No Known Activations