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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 91503
    Prev
    Next
    INDEX
    Explanations

    suffixes related to states, conditions, and actions

    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
     arşivlendi
    -0.50
    pecabe
    -0.49
    StoryboardSegue
    -0.48
    ihnach
    -0.46
    pantalón
    -0.45
     néglig
    -0.44
    ształ
    -0.44
     bezeichneter
    -0.44
    características
    -0.44
     propOrder
    -0.43
    POSITIVE LOGITS
    ⓧ
    0.60
    quiao
    0.51
    kegaard
    0.49
    arithmic
    0.48
    cosm
    0.47
    riwal
    0.46
     faptul
    0.46
    mannian
    0.44
    kuuta
    0.44
    hamshire
    0.44
    Activations Density 0.223%

    No Known Activations