Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 109969
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their actions, particularly in the context of competition or conflict

    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
     Gou
    -1.99
    Gou
    -1.82
     gou
    -1.80
    gou
    -1.48
     Gour
    -0.85
    Gour
    -0.70
     gour
    -0.66
     gourd
    -0.61
     Kou
    -0.59
    gour
    -0.57
    POSITIVE LOGITS
    GOTREF
    0.66
     NUKAT
    0.49
    twimg
    0.48
    #+#
    0.47
    ChildScrollView
    0.46
     Unwin
    0.46
    最快更新
    0.46
     Meksiku
    0.45
     invokevirtual
    0.44
    лтамалар
    0.43
    Activations Density 0.001%

    No Known Activations