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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11576
    Prev
    Next
    INDEX
    Explanations

    code-related elements specifically dealing with database session management and query execution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.45
    tanooga
    -0.38
    hematical
    -0.38
     dimaksud
    -0.37
    zeera
    -0.37
    Obrázky
    -0.34
     ausges
    -0.34
     trả
    -0.33
    wußt
    -0.33
     Sprecher
    -0.33
    POSITIVE LOGITS
    hibernate
    0.90
     CoreData
    0.86
    Hibernate
    0.82
    NamedQuery
    0.75
     JpaRepository
    0.69
     Hibernate
    0.69
    bernate
    0.69
     sessionFactory
    0.66
    openSession
    0.66
    EntityManager
    0.65
    Activations Density 0.285%

    No Known Activations