© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110206
    Prev
    Next
    INDEX
    Explanations

    variations of the word "cape."

    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
    cape
    -2.17
    capes
    -1.85
    scape
    -1.50
    Scape
    -1.46
    SCAPE
    -1.43
    caping
    -1.31
    CAPE
    -1.17
     cape
    -1.15
     scape
    -1.09
    caped
    -1.04
    POSITIVE LOGITS
     ModelExpression
    0.44
    Filmographie
    0.37
    antd
    0.37
    AutoField
    0.36
     phía
    0.36
    嘛
    0.32
     mourut
    0.32
    Referee
    0.31
     grø
    0.31
     Normdatei
    0.31
    Activations Density 0.001%

    No Known Activations