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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109809
    Prev
    Next
    INDEX
    Explanations

    references to different types of cabbage and related vegetables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     cabbage
    -1.86
     Cabbage
    -1.53
    Cabbage
    -1.43
    白菜
    -0.69
     cauliflower
    -0.68
    キャベツ
    -0.68
    bbage
    -0.68
     cab
    -0.66
     CAB
    -0.65
    Cab
    -0.59
    POSITIVE LOGITS
     EconPapers
    0.53
    tvguidetime
    0.42
    delwed
    0.38
    /**
    0.38
    <?
    0.37
     Zusammen
    0.36
    AutoScaleMode
    0.36
     كومونز
    0.35
     iprot
    0.35
    DockStyle
    0.34
    Activations Density 0.001%

    No Known Activations