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. 36489
    Prev
    Next
    INDEX
    Explanations

    words related to the design and construction of objects or systems

    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
     juges
    -0.48
     Occidente
    -0.47
    gól
    -0.46
     itſelf
    -0.45
     Majefty
    -0.44
     Füßen
    -0.43
     Inscrivez
    -0.42
     Voyez
    -0.42
    ſelf
    -0.42
     universelle
    -0.42
    POSITIVE LOGITS
     يتيمه
    0.70
     Numerade
    0.63
    warted
    0.61
    PreferredItem
    0.58
     Engineered
    0.56
    uced
    0.56
    <?
    0.56
    retweeted
    0.54
    haped
    0.54
     Sma
    0.54
    Activations Density 0.234%

    No Known Activations