© 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. 2-GEMMASCOPE-RES-16K
    6. 13572
    Prev
    Next
    INDEX
    Explanations

    references to the ear and ear-related items or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omiast
    -0.46
    lewati
    -0.46
     seragam
    -0.44
    retain
    -0.43
    MetaObject
    -0.40
     financeiro
    -0.39
     voorbij
    -0.38
    fondos
    -0.38
     mutual
    -0.38
     kandang
    -0.36
    POSITIVE LOGITS
     ear
    0.96
    Ear
    0.86
     EAR
    0.84
     Ear
    0.82
    ear
    0.77
     Layer
    0.69
    layer
    0.68
     earl
    0.67
    Layer
    0.65
     layer
    0.64
    Activations Density 0.115%

    No Known Activations