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. 109715
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "other" in various contexts

    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
    contentLoaded
    -0.52
     propOrder
    -0.45
    ंदीखरीदारी
    -0.42
     NSCoder
    -0.41
    帖最后由
    -0.41
     dép
    -0.39
    Gweler
    -0.38
    ″]
    -0.38
    anément
    -0.36
     demás
    -0.35
    POSITIVE LOGITS
    ceğine
    0.61
    SBATCH
    0.49
     junta
    0.47
     isShow
    0.46
    VYMaps
    0.46
     chatter
    0.45
     setShow
    0.45
     JMenuItem
    0.45
    guigu
    0.44
    vVar
    0.44
    Activations Density 0.007%

    No Known Activations