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. 4-GEMMASCOPE-MLP-65K
    6. 2
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "recorded."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.4.hook_mlp_out
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recorded
    -2.13
    recorded
    -1.75
     Recorded
    -1.74
    Recorded
    -1.71
     RECORD
    -1.10
     enregistré
    -1.09
     documented
    -1.05
     recording
    -1.02
     record
    -1.01
     enregist
    -0.98
    POSITIVE LOGITS
    ScopeManager
    0.82
    VersionUID
    0.68
    ViewImports
    0.66
     contextLoads
    0.65
    ритори
    0.61
    amaño
    0.60
     Infórmanos
    0.60
    Viitteet
    0.60
    writeField
    0.59
     متعلقه
    0.57
    Activations Density 0.020%

    No Known Activations