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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8616
    Prev
    Next
    INDEX
    Explanations

    negative evaluations or criticisms, particularly in creative contexts

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     الحره
    -0.39
     TextAppearance
    -0.35
     tiêu
    -0.34
     seta
    -0.32
    volut
    -0.32
     <<<<<<<<<<<<<<
    -0.31
     feine
    -0.31
    Сообщение
    -0.31
     withheld
    -0.30
    즐
    -0.30
    POSITIVE LOGITS
     buruk
    0.64
     awkward
    0.62
     abomination
    0.60
     hideous
    0.59
     يتيمه
    0.58
     monstros
    0.58
     terrible
    0.58
     awkwardly
    0.57
     poor
    0.56
     bizarre
    0.54
    Activations Density 0.306%

    No Known Activations