© 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. 23126
    Prev
    Next
    INDEX
    Explanations

    pronouns and their relationships to entities or actions

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

    it encodes or operates

    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
    出版年
    -0.56
     незавершена
    -0.55
     doInBackground
    -0.54
    StoryboardSegue
    -0.53
     createSprite
    -0.52
    ніципалі
    -0.52
    OrBuilder
    -0.50
    EClass
    -0.49
    WaitGroup
    -0.49
    ᅠ
    -0.48
    POSITIVE LOGITS
    tinyos
    0.35
     nuanced
    0.35
    MessageOf
    0.35
    fficients
    0.34
     otomatig
    0.34
     côtes
    0.33
     neumáticos
    0.33
     nahilalakip
    0.32
     saisir
    0.32
    écran
    0.32
    Activations Density 0.189%

    No Known Activations