© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 311
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and function-related components in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.96
     للاسماء
    -0.93
     CreateTagHelper
    -0.91
    <unused99>
    -0.90
    UserScript
    -0.90
    ThroughAttribute
    -0.88
     كومونز
    -0.88
    تقاوى
    -0.88
     surla
    -0.88
    ⒝
    -0.88
    POSITIVE LOGITS
     zijne
    0.30
     srdce
    0.29
     varandra
    0.28
     Einfluß
    0.24
     étoit
    0.22
     sebou
    0.21
     hlavy
    0.19
     feroit
    0.18
     hvě
    0.18
     stället
    0.17
    Activations Density 1.316%

    No Known Activations