© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 109290
    Prev
    Next
    INDEX
    Explanations

    references to the location Oakland and associated entities

    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
    Oakland
    -1.55
     Oakland
    -1.54
    OAK
    -0.73
    oa̍t
    -0.65
     OAK
    -0.64
     InputDecoration
    -0.60
    Tikang
    -0.58
    oak
    -0.53
     transfieras
    -0.50
     nahilalakip
    -0.50
    POSITIVE LOGITS
     createState
    0.53
    unken
    0.38
     ExecuteAsync
    0.37
    änemark
    0.37
     original
    0.36
    AnchorTagHelper
    0.35
     unre
    0.35
    onha
    0.34
     flare
    0.33
     Deputy
    0.33
    Activations Density 0.001%

    No Known Activations