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. 101421
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to software development and web applications

    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
    SequentialGroup
    -0.47
     Low
    -0.40
    Low
    -0.37
    ftagPool
    -0.37
    ⎦
    -0.36
    matchCondition
    -0.34
     <=",
    -0.34
     Lower
    -0.34
     banned
    -0.34
     Simmons
    -0.33
    POSITIVE LOGITS
     فريبيس
    0.75
     GenerationType
    0.63
     betweenstory
    0.54
    AndEndTag
    0.54
    RectangleBorder
    0.53
     AssemblyProduct
    0.49
    المكان
    0.48
    invokeLater
    0.46
    NameInMap
    0.46
    Datuak
    0.44
    Activations Density 0.052%

    No Known Activations