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
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15013
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs, particularly those that define or manage execution flows, data structures, and criteria in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
    expandindo
    -0.72
     Meksiku
    -0.63
     Italijanski
    -0.61
     Италијани
    -0.61
    الحياه
    -0.60
     utafitiHapana
    -0.60
    تقاوى
    -0.59
    səhifə
    -0.59
     Walkover
    -0.54
    сылкі
    -0.53
    POSITIVE LOGITS
     AssemblyTitle
    0.46
    ConstraintMaker
    0.46
     violación
    0.44
     costumbre
    0.41
     ModelExpression
    0.41
     respiración
    0.41
     prisión
    0.40
     Gestão
    0.38
     cárcel
    0.37
     campanha
    0.37
    Activations Density 0.794%

    No Known Activations