© 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. 12-GEMMASCOPE-RES-16K
    6. 6081
    Prev
    Next
    INDEX
    Explanations

    phrases that reference "the rest of" something, indicating additional information or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Muhamma
    -0.56
    UAWEI
    -0.51
    channelId
    -0.50
     gyhoeddwyd
    -0.45
    mappedBy
    -0.45
     Guille
    -0.44
     câmera
    -0.42
    äure
    -0.42
     actionTypes
    -0.42
     comboBox
    -0.42
    POSITIVE LOGITS
     rest
    1.50
     Rest
    1.42
    Rest
    1.41
    rest
    1.38
    REST
    1.16
     REST
    1.16
     rested
    1.02
     rests
    1.02
     resten
    0.95
     resting
    0.92
    Activations Density 0.155%

    No Known Activations