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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 25693
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to beauty and scenery

    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
    expandindo
    -0.73
    Tikang
    -0.68
    
    -0.66
    ########.
    -0.66
    writeFieldEnd
    -0.63
     Monfieur
    -0.61
     bezeichneter
    -0.59
     informée
    -0.58
    Izvori
    -0.57
    majánló
    -0.57
    POSITIVE LOGITS
     scenery
    0.69
     picturesque
    0.66
     scenic
    0.63
     beautiful
    0.59
     landscapes
    0.55
    beautiful
    0.54
     surrounding
    0.52
     pięk
    0.47
     đẹp
    0.45
     landscape
    0.45
    Activations Density 0.009%

    No Known Activations