© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 35420
    Prev
    Next
    INDEX
    Explanations

    instances of the word "now" and its variations, indicating urgency or immediacy

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

    starting a sentence or clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🇶
    -0.36
    mybatisplus
    -0.35
     estructuras
    -0.33
     estrut
    -0.32
     doute
    -0.32
    Morfologia
    -0.31
     strukt
    -0.31
     structures
    -0.30
     Imperio
    -0.30
    はじめに
    -0.30
    POSITIVE LOGITS
     BoxFit
    0.69
     CreateTagHelper
    0.65
    Now
    0.65
    InputBorder
    0.63
     onPostExecute
    0.61
    NOW
    0.57
     doInBackground
    0.56
    WebVitals
    0.55
     useAppContext
    0.54
     Now
    0.53
    Activations Density 0.025%

    No Known Activations