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. 0-GEMMASCOPE-MLP-16K
    6. 49
    Prev
    Next
    INDEX
    Explanations

    titles or designations of people, particularly formal ones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    titles and formal titles used for individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mr
    -0.97
    Mr
    -0.89
    engagent
    -0.65
    AxisAlignment
    -0.63
    findpost
    -0.62
    بوابة
    -0.58
     Ms
    -0.58
    prüche
    -0.57
    ConstraintMaker
    -0.57
     آقای
    -0.56
    POSITIVE LOGITS
     lenker
    0.61
     חיצוניים
    0.56
     صوتيه
    0.51
    ganu
    0.48
     desemple
    0.48
     mercancías
    0.47
     отъ
    0.45
     textStatus
    0.45
     délé
    0.45
     náz
    0.44
    Activations Density 0.769%

    No Known Activations