© 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. 109303
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to," particularly when related to actions or intentions

    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
    :✨
    -0.65
    izr
    -0.57
     gynhyrchwyd
    -0.53
    principalColumn
    -0.48
    ьаж
    -0.48
    ReusableCell
    -0.47
     Grüsse
    -0.47
    bitField
    -0.45
     propOrder
    -0.44
    ſelves
    -0.44
    POSITIVE LOGITS
    inSlope
    0.45
     General
    0.42
     comuniques
    0.40
     International
    0.40
    outSlope
    0.36
     Lang
    0.35
    underbrace
    0.35
    WriteBarrier
    0.35
     Mayor
    0.35
    exitRule
    0.34
    Activations Density 0.001%

    No Known Activations