© 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-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15682
    Prev
    Next
    INDEX
    Explanations

    terms related to loss and absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.46
    Ārējās
    -0.43
    +:+
    -0.41
    awtextra
    -0.40
     Wicidata
    -0.40
    EndGlobalSection
    -0.40
    StringCopy
    -0.40
    RTLR
    -0.39
    isNotBlank
    -0.39
     oleo
    -0.39
    POSITIVE LOGITS
     loss
    1.42
     lost
    1.23
     Loss
    1.22
    Loss
    1.17
     losses
    1.17
     LOSS
    1.16
     losing
    1.14
    Losing
    1.11
     lose
    1.10
     loses
    1.10
    Activations Density 0.328%

    No Known Activations