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. 0-GEMMASCOPE-MLP-16K
    6. 68
    Prev
    Next
    INDEX
    Explanations

    the word "got" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances of the word "got" in various forms and 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-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     got
    -1.80
    got
    -1.24
    Got
    -1.21
     Got
    -1.02
     had
    -0.82
     GOT
    -0.73
     gotta
    -0.67
     gotcha
    -0.64
     gott
    -0.64
    chtigkeit
    -0.61
    POSITIVE LOGITS
    ])).
    0.85
    ]));
    
    0.66
    '},
    
    0.65
    })).
    0.62
     onPostExecute
    0.62
    erialize
    0.61
    ])[
    0.61
    />
    
    0.61
    MigrationBuilder
    0.61
    gridx
    0.61
    Activations Density 0.044%

    No Known Activations