© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12267
    Prev
    Next
    INDEX
    Explanations

    closing braces and brackets in mathematical expressions or code

    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
    ?>">
    -1.03
    ?>
    -0.87
    tagHelperRunner
    -0.60
    zer
    -0.53
    ون
    -0.49
    ner
    -0.47
    ==$
    -0.47
    ?><
    -0.46
    Thus
    -0.46
    ta
    -0.46
    POSITIVE LOGITS
     SwitchCompat
    0.74
    CloseOperation
    0.71
     للمعارف
    0.68
    tagHelper
    0.65
     للاسماء
    0.64
    WithIOException
    0.63
    Drupal
    0.61
    kadot
    0.61
    ulitis
    0.61
    Zeneca
    0.60
    Activations Density 0.235%

    No Known Activations