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. 1-GEMMASCOPE-MLP-16K
    6. 8886
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'a' 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 @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -2.44
     an
    -2.00
     sebuah
    -1.11
     eine
    -1.04
     einen
    -1.03
     seorang
    -1.01
     einem
    -1.01
     isang
    -1.00
    einem
    -1.00
     Sebuah
    -0.99
    POSITIVE LOGITS
     AttributeSet
    0.64
    ComponentScan
    0.58
    AutoScaleMode
    0.55
    +#+#
    0.55
    InputBorder
    0.55
     Roskov
    0.54
     Italijanski
    0.54
    曖昧さ回避
    0.54
     Acton
    0.53
     ArrayAdapter
    0.52
    Activations Density 0.425%

    No Known Activations