© 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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1239
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical assembly and repairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MergeFrom
    -0.68
     للمعارف
    -0.64
     gynnwys
    -0.60
     AssemblyTitle
    -0.58
    SerializedSize
    -0.56
    esteld
    -0.55
    avigation
    -0.54
     ExecuteAsync
    -0.52
     jurí
    -0.51
    raszamy
    -0.51
    POSITIVE LOGITS
     removal
    2.17
     removed
    2.05
     remove
    2.00
     Removal
    1.93
     removing
    1.93
     Remove
    1.80
     REMOV
    1.77
     Removing
    1.77
    removal
    1.75
    Removal
    1.75
    Activations Density 0.682%

    No Known Activations