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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 82704
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "init" and its variations, which are typically related to initialization functions in programming contexts

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

    init and initialization tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pageNumber
    -0.65
     statusCode
    -0.58
     fileSize
    -0.57
     errorMessage
    -0.55
     numberOfRows
    -0.54
     jsonArray
    -0.53
     للمعارف
    -0.53
     élas
    -0.52
     vectorielle
    -0.52
     varandra
    -0.51
    POSITIVE LOGITS
    init
    1.77
     init
    1.66
    Init
    1.40
     Init
    1.34
    INIT
    1.32
     INIT
    1.27
     initi
    0.99
     initiation
    0.95
     initialization
    0.94
     Initi
    0.93
    Activations Density 0.008%

    No Known Activations