© 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. 44927
    Prev
    Next
    INDEX
    Explanations

    key components and significant aspects of inventions or features

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

    another example or aspect

    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
     Komunikasi
    -0.40
     always
    -0.40
     Capacidad
    -0.38
    alyptus
    -0.36
     asegu
    -0.36
     Evaluación
    -0.36
     conmigo
    -0.35
     Profitez
    -0.33
     pleg
    -0.33
     Pues
    -0.33
    POSITIVE LOGITS
     another
    1.27
    another
    1.16
    Another
    1.09
     Another
    1.05
     ANOTHER
    1.02
     otra
    0.81
    另一個
    0.80
    อีก
    0.80
     otro
    0.77
    altra
    0.77
    Activations Density 0.091%

    No Known Activations