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. 6-GEMMASCOPE-MLP-16K
    6. 171
    Prev
    Next
    INDEX
    Explanations

    terms related to responsibilities and ownership in agreements or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.73
     Walkover
    -0.67
    +#+
    -0.67
     estekak
    -0.65
    intios
    -0.64
     supremacy
    -0.63
    ịch
    -0.63
     control
    -0.63
     Kontrolle
    -0.61
    最快更新
    -0.58
    POSITIVE LOGITS
     seno
    0.53
    GOTREF
    0.51
    AutoField
    0.47
    toed
    0.47
    fvar
    0.47
    PSON
    0.45
     Dostupné
    0.44
    instant
    0.43
     mema
    0.43
    كويكب
    0.42
    Activations Density 0.695%

    No Known Activations