© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8557
    Prev
    Next
    INDEX
    Explanations

    terms related to loss or reduction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    complexContent
    -1.03
    OGND
    -1.02
     referenties
    -0.99
    theless
    -0.92
    QMetaType
    -0.90
     complémentaires
    -0.89
    Datuak
    -0.88
     Paesi
    -0.85
    Portail
    -0.82
     вікі
    -0.82
    POSITIVE LOGITS
     loss
    1.58
     Loss
    1.51
     LOSS
    1.41
    loss
    1.41
    Loss
    1.38
     losses
    1.26
    LOSS
    1.21
    rdida
    1.12
     Losses
    1.10
    losses
    1.07
    Activations Density 0.049%

    No Known Activations