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. 174
    Prev
    Next
    INDEX
    Explanations

    objects and items associated with various food and musical themes

    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
    GEBURTSDATUM
    -0.81
    />";
    -0.79
    EndContext
    -0.77
     Roskov
    -0.76
    ']")
    -0.74
    HideFlags
    -0.74
    Personendaten
    -0.71
    تقاوى
    -0.71
    Hentet
    -0.71
    bewerken
    -0.69
    POSITIVE LOGITS
    pielt
    0.47
     absent
    0.41
    mahaman
    0.38
     box
    0.38
    l
    0.38
    box
    0.36
    haltens
    0.35
    也知道
    0.34
     militare
    0.34
    jà
    0.34
    Activations Density 0.378%

    No Known Activations