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. 65
    Prev
    Next
    INDEX
    Explanations

    bracket symbols in various contexts, indicating code or data structures

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

    strings or sequences related to brackets or list notation

    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
    [
    -1.84
    (
    -1.18
    \
    -1.03
    “
    -1.03
    $
    -0.93
    <
    -0.90
    #
    -0.87
    *
    -0.84
    &
    -0.82
    []
    -0.81
    POSITIVE LOGITS
    )");
    
    0.91
    ."]
    0.89
    :");
    0.88
    ".
    
    0.85
    "]];
    0.85
    ])):
    0.84
    ":
    
    0.83
     myſelf
    0.82
     ſeveral
    0.82
    }%
    
    0.82
    Activations Density 0.098%

    No Known Activations