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. 5
    Prev
    Next
    INDEX
    Explanations

    references to regulatory bodies and organizations related to reproductive and tissue banking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names of organizations and official governmental departments.

    oai_token-act-pair · gpt-4oTriggered by @pigeonzow
    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
     rest
    -0.57
    gerufen
    -0.51
    らか
    -0.47
    Rest
    -0.46
    mak
    -0.46
     rested
    -0.45
    śnie
    -0.45
    RLock
    -0.44
     adatt
    -0.43
     otot
    -0.42
    POSITIVE LOGITS
    posedge
    0.76
    ArrowToggle
    0.73
    WithIOException
    0.72
     ostavi
    0.70
     SwitchCompat
    0.70
     للمعارف
    0.69
    الحياه
    0.68
    MigrationBuilder
    0.67
    balleur
    0.66
     esternos
    0.66
    Activations Density 0.219%

    No Known Activations