© 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. 25-GEMMASCOPE-RES-16K
    6. 5640
    Prev
    Next
    INDEX
    Explanations

    references to null or empty values and their associated interfaces in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "));
    
    -1.56
    '));
    
    -1.48
    '));
    -1.47
    "));
    -1.43
    ')).
    -1.26
    ”).
    -1.22
    ")).
    -1.22
     "));
    -1.19
    ()));
    -1.19
    ()));
    
    -1.18
    POSITIVE LOGITS
    esModule
    0.72
    ImageContext
    0.53
    ){
    0.53
    HasBeenSet
    0.52
    Geplaatst
    0.52
     maka
    0.52
     then
    0.49
     thì
    0.49
    enumi
    0.49
     allora
    0.48
    Activations Density 0.105%

    No Known Activations