© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 63383
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and code structure

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

    code and alias definitions

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    OGND
    -0.48
     useCallback
    -0.48
     strøm
    -0.48
     ruido
    -0.44
     recomendaciones
    -0.43
     gevallen
    -0.42
     forhold
    -0.41
     doInBackground
    -0.41
     waarbij
    -0.40
     Bowles
    -0.40
    POSITIVE LOGITS
     tartalomajánló
    0.64
    хьтан
    0.61
    
    0.61
     Мексичка
    0.59
    لينكات
    0.52
     للاسماء
    0.51
     Chwiliwch
    0.50
    TagNumber
    0.48
    hoeddwyd
    0.48
    تقاوى
    0.48
    Activations Density 0.007%

    No Known Activations