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. 34
    Prev
    Next
    INDEX
    Explanations

    sequences of underscores or dashes that may indicate a break or separation in text or content

    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
    MENAFN
    -0.62
    fjspx
    -0.57
     مرئيه
    -0.56
    GEBURTS
    -0.56
    pyx
    -0.54
    racene
    -0.53
     kasarigan
    -0.53
    
    -0.53
    Посилання
    -0.49
    trà
    -0.49
    POSITIVE LOGITS
    <bos>
    0.60
    VersionUID
    0.57
    SBATCH
    0.54
     >=",
    0.50
     Scritto
    0.50
    imine
    0.50
    atguigu
    0.49
     समीक्षाओं
    0.49
    __":
    
    0.48
    glMatrixMode
    0.47
    Activations Density 0.508%

    No Known Activations