© 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. 110173
    Prev
    Next
    INDEX
    Explanations

    references to a specific property named "Red River."

    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
    antaranya
    -0.40
    posas
    -0.39
     puertos
    -0.38
     cumplido
    -0.38
    áfrica
    -0.37
    arroll
    -0.36
     conciencia
    -0.36
     funcionales
    -0.36
    lottesville
    -0.36
    viembre
    -0.35
    POSITIVE LOGITS
     ProtoMessage
    0.67
    存于互联网档案馆
    0.59
    IndentedString
    0.54
    enterOuterAlt
    0.51
    oa̍t
    0.51
     HasFactory
    0.49
    LabelTagHelper
    0.48
     StatelessWidget
    0.48
     виправивши
    0.48
    ChrTalk
    0.47
    Activations Density 0.065%

    No Known Activations