© 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. 3-GEMMASCOPE-RES-16K
    6. 2161
    Prev
    Next
    INDEX
    Explanations

    the prefix "pre-" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $}}
    -0.75
    .*")]
    -0.74
    
    -0.73
    TypedDataSet
    -0.73
     Wallflower
    -0.70
    Modifica
    -0.69
     Tourisme
    -0.69
     CiNii
    -0.68
     LCCN
    -0.68
    ^(@)
    -0.67
    POSITIVE LOGITS
     pre
    3.18
    Pre
    3.16
     Pre
    3.10
    pre
    2.97
     PRE
    2.78
    PRE
    2.70
     pré
    2.31
     Pré
    1.87
    预
    1.86
    Pré
    1.80
    Activations Density 0.085%

    No Known Activations