© 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. 0-GEMMASCOPE-RES-16K
    6. 7628
    Prev
    Next
    INDEX
    Explanations

    terms related to coding and programming functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suono
    -0.42
     reputación
    -0.42
     neón
    -0.42
     afuera
    -0.42
    šanās
    -0.39
     anillos
    -0.39
     mükemmel
    -0.39
     الحره
    -0.38
     незавершена
    -0.38
    TargetException
    -0.38
    POSITIVE LOGITS
    方
    0.56
     Rabbit
    0.55
     diplom
    0.55
     Mono
    0.55
     monos
    0.53
     Vill
    0.52
     obli
    0.52
     tick
    0.52
     ere
    0.51
    Vill
    0.51
    Activations Density 1.994%

    No Known Activations