Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 109598
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional states and psychological attributes

    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
    principalColumn
    -0.68
    ContentAsync
    -0.63
    enumii
    -0.53
    DockStyle
    -0.52
     الرياضيه
    -0.52
    unknownFields
    -0.49
     الحره
    -0.48
    󠁢
    -0.48
    addPreferredGap
    -0.48
    Hozzáférés
    -0.47
    POSITIVE LOGITS
    styleable
    0.46
     Tre
    0.38
     tvb
    0.37
     graduation
    0.36
    tre
    0.36
     Rome
    0.35
     soft
    0.35
     absence
    0.34
    ness
    0.34
     imple
    0.33
    Activations Density 0.548%

    No Known Activations