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. 112
    Prev
    Next
    INDEX
    Explanations

    concepts related to significance, unity, and relational dynamics in various contexts

    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
    DockStyle
    -0.67
     دیکھیے
    -0.61
    AutoField
    -0.54
    MessageOf
    -0.54
     فريبيس
    -0.54
     MainAxisSize
    -0.52
    offsetof
    -0.52
     CreateTagHelper
    -0.51
     nära
    -0.51
    ieta
    -0.50
    POSITIVE LOGITS
    HtmlAttribute
    0.63
    )++;
    0.60
    ButterKnife
    0.57
    ]--;
    0.57
    InvalidProtocol
    0.57
    $")
    0.54
    BitConverter
    0.52
    chestra
    0.52
    GraphicsUnit
    0.50
    fecture
    0.48
    Activations Density 0.595%

    No Known Activations