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. 15862
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 's'

    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
     Normdatei
    -0.63
    blica
    -0.54
    Kaynakça
    -0.54
    AccessorTable
    -0.51
     Приступљено
    -0.50
     estimés
    -0.49
    setSubject
    -0.47
    Yer
    -0.47
    WriteBarrier
    -0.47
    клопе
    -0.46
    POSITIVE LOGITS
    findpost
    0.72
    exitRule
    0.63
     track
    0.52
    onia
    0.51
    LayoutPanel
    0.49
     Eins
    0.48
     تضيفلها
    0.48
    peza
    0.48
    asam
    0.47
    UnsafeEnabled
    0.47
    Activations Density 0.051%

    No Known Activations