Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109524
    Prev
    Next
    INDEX
    Explanations

    bits of information related to various forms of insurance and corresponding examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SqlClient
    -0.57
     Latter
    -0.56
     restri
    -0.55
    momix
    -0.54
     Recom
    -0.54
     Desc
    -0.54
     Fore
    -0.53
    ArrowToggle
    -0.52
     Opening
    -0.52
     Ue
    -0.52
    POSITIVE LOGITS
    utilisons
    0.56
     casada
    0.45
     незавершена
    0.45
     autorytatywna
    0.44
    новништво
    0.43
     zijne
    0.43
     unknownFields
    0.41
     gwia
    0.41
    ValueStyle
    0.40
     elämä
    0.40
    Activations Density 0.486%

    No Known Activations