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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120818
    Prev
    Next
    INDEX
    Explanations

    various quoted speech or expressions

    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
     betweenstory
    -0.78
    httphttps
    -0.60
    Vidite
    -0.60
    ///</
    -0.58
    CppMethod
    -0.57
     invokingState
    -0.54
    GEBURTSDATUM
    -0.54
    ]=>
    -0.52
    ➟
    -0.52
     &___
    -0.50
    POSITIVE LOGITS
     виправивши
    0.39
     cr
    0.36
    Cry
    0.35
     Maybe
    0.35
     Cry
    0.34
     giveaway
    0.33
    wear
    0.33
     Cool
    0.33
     audience
    0.32
     Pull
    0.32
    Activations Density 0.435%

    No Known Activations