Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 102480
    Prev
    Next
    INDEX
    Explanations

    closing braces and indentation in code segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    المناصب
    -0.63
    
    -0.63
    PyExc
    -0.63
    tvguidetime
    -0.60
     disambiguazione
    -0.59
     OFDb
    -0.59
     nonUne
    -0.58
    ikusbot
    -0.57
     Taktlose
    -0.57
    منابع
    -0.57
    POSITIVE LOGITS
     Gestión
    0.42
     Formación
    0.41
     Trabajo
    0.38
     and
    0.36
     Herramientas
    0.36
     nomme
    0.35
     Stärke
    0.35
     Komunikasi
    0.35
     Educación
    0.35
    synthesize
    0.34
    Activations Density 0.003%

    No Known Activations