© 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. 110107
    Prev
    Next
    INDEX
    Explanations

    keywords related to historic preservation and recognition

    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
     Historic
    -1.63
    Historic
    -1.52
    historic
    -1.16
     Historical
    -1.16
     HISTOR
    -1.14
    Historical
    -1.09
     historic
    -1.07
    HISTOR
    -1.05
     HISTORICAL
    -0.98
    historical
    -0.89
    POSITIVE LOGITS
     sing
    0.32
     Sing
    0.28
     visi
    0.28
    estimable
    0.27
     않았
    0.26
     moment
    0.26
    setAlignment
    0.26
    elif
    0.25
    hofer
    0.25
     satisfa
    0.25
    Activations Density 0.005%

    No Known Activations