Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 30960
    Prev
    Next
    INDEX
    Explanations

    instances of array or list structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.48
     '*')
    -0.46
     fileSize
    -0.45
     maxX
    -0.45
     parentId
    -0.44
    ``.
    -0.44
    RegressionTest
    -0.43
    tinyos
    -0.43
    gameserver
    -0.42
     @"";
    -0.42
    POSITIVE LOGITS
     useState
    0.91
    useState
    0.76
     defaultstate
    0.59
     initComponents
    0.57
     [
    0.55
     propOrder
    0.54
     makeStyles
    0.52
    GEBURTSDATUM
    0.52
     Roskov
    0.50
     acceptez
    0.50
    Activations Density 0.000%

    No Known Activations