© 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. 110265
    Prev
    Next
    INDEX
    Explanations

    instances of strong emotional expressions, particularly those related to frustration or anger

    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
    ToListAsync
    -0.46
    FailureListener
    -0.44
    NameInMap
    -0.43
    ########.
    -0.40
     localVar
    -0.40
     sessionFactory
    -0.39
     صوتيه
    -0.39
    Etimología
    -0.38
    vician
    -0.38
    AxisAlignment
    -0.38
    POSITIVE LOGITS
    الحياه
    0.56
    Personensuche
    0.47
     kaarangay
    0.43
    ROD
    0.40
    Kare
    0.40
     Siro
    0.40
    dsn
    0.39
    ativement
    0.39
    Sar
    0.38
    esModule
    0.38
    Activations Density 0.032%

    No Known Activations