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-2-2B
    4. MLP Out - 65k
    5. 18-GEMMASCOPE-MLP-65K
    6. 31
    Prev
    Next
    INDEX
    Explanations

    financial amounts and numerical values related to debts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.18.hook_mlp_out
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.65
     ujednoznacz
    -0.45
    __(/*!
    -0.45
    ENSES
    -0.44
    ingale
    -0.44
    ANTAGES
    -0.44
    posedge
    -0.43
     magát
    -0.43
     ComVisible
    -0.42
     franceses
    -0.42
    POSITIVE LOGITS
    enumii
    0.68
    SOUNDBITE
    0.68
    RenderAtEndOf
    0.67
    uxxxx
    0.63
    __':
    
    0.60
    PMailer
    0.59
     Terraria
    0.59
    सन्दर्भ
    0.57
    adaptiveStyles
    0.56
     Guilty
    0.55
    Activations Density 0.172%

    No Known Activations