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 - 65k
    5. 0-GEMMASCOPE-MLP-65K
    6. 60889
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Name" 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 @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Name
    -1.36
    NAME
    -0.81
    MemoryWarning
    -0.73
    All
    -0.69
     فريبيس
    -0.66
    This
    -0.65
    Type
    -0.62
    Tikang
    -0.62
     Name
    -0.62
    name
    -0.61
    POSITIVE LOGITS
    SharedDtor
    0.91
    "):
    
    0.82
    ']))
    
    0.81
    }?
    0.79
    >");
    
    0.76
    }*/
    
    0.75
    '):
    
    0.75
    '];?>
    0.75
    )");
    
    0.75
    ?
    
    0.74
    Activations Density 0.013%

    No Known Activations