© 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. 110132
    Prev
    Next
    INDEX
    Explanations

    terms associated with melting and the process of melting various substances

    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
     melt
    -1.81
     melts
    -1.61
     melted
    -1.59
     Melt
    -1.55
    Melt
    -1.46
    melt
    -1.42
     melting
    -1.39
     Melting
    -1.16
    melting
    -1.09
    Melting
    -1.02
    POSITIVE LOGITS
     betweenstory
    0.46
    TagMode
    0.45
     ostavi
    0.44
    exitRule
    0.43
    🦵
    0.41
     CURIAM
    0.41
    Географиясе
    0.41
    StoryboardSegue
    0.40
    xase
    0.39
    PRNewswire
    0.39
    Activations Density 0.002%

    No Known Activations