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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 8940
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their patterns in sentences

    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
    AccessorTable
    -0.61
    SourceChecksum
    -0.59
     שוליים
    -0.55
    ]--;
    -0.54
    []);
    -0.53
    Hochspringen
    -0.52
     dAtA
    -0.50
    =""/>
    -0.49
     بتاريخ
    -0.49
    elemField
    -0.49
    POSITIVE LOGITS
    enfone
    0.66
     surla
    0.61
    UseVisualStyle
    0.60
     సౌకర్య
    0.58
    Partly
    0.57
    StructEnd
    0.57
    VIATIONS
    0.57
     CascadeType
    0.55
     BorderSide
    0.54
    lioma
    0.53
    Activations Density 1.185%

    No Known Activations