© 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. 22-GEMMASCOPE-RES-16K
    6. 2605
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "new" and its associations with objects, particularly Date and File instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code related to creating or using dates

    np_acts-logits-general · gemini-2.0-flash

    new object instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAsync
    -0.61
     InputDecoration
    -0.54
    }|\
    -0.52
    ensement
    -0.51
    RequestMapping
    -0.48
     doInBackground
    -0.46
    SuppressLint
    -0.46
    astă
    -0.45
     linkovi
    -0.43
     والس
    -0.42
    POSITIVE LOGITS
    UserScript
    0.75
    RegressionTest
    0.73
     يتيمه
    0.67
     Array
    0.67
     Promise
    0.62
     Date
    0.62
    зулта
    0.62
     Object
    0.59
     window
    0.58
     متعلقه
    0.57
    Activations Density 0.135%

    No Known Activations