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. 22-GEMMASCOPE-MLP-16K
    6. 15818
    Prev
    Next
    INDEX
    Explanations

    references to political repression and advocacy for freedoms and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.88
     חיצוניים
    -0.75
     lenker
    -0.71
    httphttps
    -0.69
    __":
    -0.65
     <=",
    -0.64
    __":
    
    -0.63
     الحره
    -0.63
    DockStyle
    -0.62
    tonsoft
    -0.61
    POSITIVE LOGITS
     break
    0.49
    iddish
    0.49
     associ
    0.49
     Break
    0.46
    register
    0.46
    break
    0.45
    ưỡi
    0.45
     Milo
    0.43
    الحياه
    0.42
     Plata
    0.42
    Activations Density 0.413%

    No Known Activations