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 - 16k
    5. 6-GEMMASCOPE-MLP-16K
    6. 184
    Prev
    Next
    INDEX
    Explanations

    dialogue and expressions of communication between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ˈ
    -0.50
    orphic
    -0.47
     follicular
    -0.47
    odle
    -0.44
    ztat
    -0.44
     abstinence
    -0.43
    ByExample
    -0.43
    oo
    -0.41
    örper
    -0.41
     /\.(
    -0.41
    POSITIVE LOGITS
    AndEndTag
    1.13
    UnusedPrivate
    0.78
    NameInMap
    0.77
    তথ্যসূত্র
    0.72
    HostException
    0.72
    Geplaatst
    0.72
     وتسجيلات
    0.71
     noDo
    0.70
    Personendaten
    0.69
    IBarButtonItem
    0.69
    Activations Density 0.384%

    No Known Activations