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. 1-GEMMASCOPE-MLP-16K
    6. 8820
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initComponents
    -0.56
    "}},
    -0.54
    맺
    -0.51
    argout
    -0.50
    =$?
    -0.49
    MessageTagHelper
    -0.47
    ASED
    -0.46
     trap
    -0.46
    ?>">
    -0.45
    ливо
    -0.45
    POSITIVE LOGITS
    +:+
    0.76
    Tikang
    0.71
    Vanjske
    0.65
     cardíaca
    0.63
     handker
    0.59
    ValueStyle
    0.58
     Touchable
    0.56
     CreateTagHelper
    0.54
     ſch
    0.54
    antiation
    0.54
    Activations Density 0.720%

    No Known Activations