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. 15794
    Prev
    Next
    INDEX
    Explanations

    references to musical instruments or individuals associated with music

    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
     CreateTagHelper
    -0.64
    SupportActionBar
    -0.60
    InjectAttribute
    -0.60
    XmlAccessorType
    -0.59
     SafeMath
    -0.58
    RenderAtEndOf
    -0.58
    autoreleasepool
    -0.58
    Rptr
    -0.57
    TestMethod
    -0.56
    těte
    -0.56
    POSITIVE LOGITS
     band
    1.18
     Band
    1.05
    band
    1.01
    Band
    0.96
     BAND
    0.92
     bands
    0.92
     trumpet
    0.92
     trump
    0.91
    bands
    0.90
    BAND
    0.89
    Activations Density 0.234%

    No Known Activations