© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8838
    Prev
    Next
    INDEX
    Explanations

    components related to customer orders and inventory management systems

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

    complex technical or business documentation containing detailed specifications and system descriptions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remb
    -0.32
    uscht
    -0.32
     OMITBAD
    -0.32
     désolés
    -0.31
     ویکی‌پدیای
    -0.30
     TECHNIQUE
    -0.30
    HttpDelete
    -0.29
     privacidad
    -0.28
    DeleteCommand
    -0.28
    stęp
    -0.28
    POSITIVE LOGITS
     ERP
    1.20
     CRM
    1.13
     automating
    1.02
     automate
    0.99
     software
    0.97
    ERP
    0.95
     automation
    0.92
    CRM
    0.90
     management
    0.89
     ticketing
    0.87
    Activations Density 0.357%

    No Known Activations