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. 87
    Prev
    Next
    INDEX
    Explanations

    text related to software licensing and compliance

    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
     fine
    -1.56
    fine
    -1.39
    Fine
    -1.37
     Fine
    -1.33
     FINE
    -1.24
    FINE
    -1.13
     finer
    -1.04
     small
    -0.94
    small
    -0.87
     finely
    -0.85
    POSITIVE LOGITS
    Tikang
    0.56
    WarningLevel
    0.51
    TabIndex
    0.49
     Signalez
    0.48
    cheiben
    0.47
    utum
    0.47
     CreateTagHelper
    0.46
     Ceinture
    0.46
     przew
    0.45
    gtest
    0.44
    Activations Density 0.291%

    No Known Activations