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

    Neuronpedia

    Jacobian LensNEW
    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
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12114
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software-defined networking and network functions virtualization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     صوتيه
    -0.43
    StringCopy
    -0.42
     StringTokenizer
    -0.40
    習慣
    -0.39
     Cru
    -0.38
    jura
    -0.38
    DataAnnotations
    -0.35
     stamped
    -0.35
    AsUp
    -0.35
    slot
    -0.35
    POSITIVE LOGITS
    HasAnnotation
    0.48
    DockStyle
    0.47
    Ecotoxicity
    0.46
     intStringLen
    0.45
     miniaturka
    0.43
     Einfluß
    0.43
     ब्रेकडाउन
    0.43
    ibrill
    0.43
    Lähteet
    0.42
    Халык
    0.42
    Activations Density 0.726%

    No Known Activations