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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 10773
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to interpersonal relationships and struggles

    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
     precisely
    -0.42
     inmediatamente
    -0.40
     précisément
    -0.39
     virtually
    -0.36
     practically
    -0.35
     approximately
    -0.35
     econó
    -0.35
     automatically
    -0.35
     nemlig
    -0.34
     essentially
    -0.33
    POSITIVE LOGITS
     AssemblyCulture
    0.83
     ब्रेकडाउन
    0.81
    AddTagHelper
    0.77
    WireFormatLite
    0.76
    出版年
    0.75
    хьтан
    0.73
    
    0.73
     transfieras
    0.69
    ècie
    0.69
    WriteTagHelper
    0.64
    Activations Density 0.149%

    No Known Activations