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. 0-GEMMASCOPE-MLP-65K
    6. 61104
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MICA
    -0.53
     ASE
    -0.52
    neath
    -0.51
    NECT
    -0.51
     cláss
    -0.51
     nämlich
    -0.50
     namelijk
    -0.49
    ljiv
    -0.49
    tled
    -0.48
    考虑到
    -0.48
    POSITIVE LOGITS
    ftagPool
    1.05
    RTEX
    0.86
     AssemblyCulture
    0.85
    libft
    0.82
    ResumeLayout
    0.81
    发表于
    0.79
    
    0.77
    rungsseite
    0.74
    TagHelpers
    0.74
    migrationBuilder
    0.74
    Activations Density 0.011%

    No Known Activations