© 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. 9555
    Prev
    Next
    INDEX
    Explanations

    references to the absence or insufficiency of something

    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
    TagMode
    -0.53
    Oops
    -0.43
     Ele
    -0.39
     dubbed
    -0.38
    元
    -0.38
     опо
    -0.37
     appropriately
    -0.37
     opted
    -0.36
     yo
    -0.36
     Eco
    -0.36
    POSITIVE LOGITS
     shortage
    1.49
     deficiency
    1.13
     shortages
    1.11
     deficit
    1.08
     lack
    1.01
     scarcity
    0.98
    situation
    0.96
     lacking
    0.96
    Lack
    0.95
     escase
    0.93
    Activations Density 0.319%

    No Known Activations