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. 15799
    Prev
    Next
    INDEX
    Explanations

    numeric data related to statistical analysis

    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
    ?”.
    -1.01
    ”).
    -1.01
    ").
    -0.97
    ?».
    -0.96
    ”。
    -0.96
    ?".
    -0.94
    }'.
    -0.93
    ’).
    -0.93
     }).
    -0.91
    }`).
    -0.91
    POSITIVE LOGITS
    .)
    1.21
    .]
    1.01
    .\
    0.78
    .>
    0.78
    .):
    0.77
    .)-
    0.77
    .)}
    0.75
    .»
    0.75
    .}
    0.74
    .-
    0.73
    Activations Density 2.747%

    No Known Activations