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. 109534
    Prev
    Next
    INDEX
    Explanations

    programming constructs and types related to system and data structures

    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
     BorderSide
    -0.44
     téléphonique
    -0.44
     partenza
    -0.43
    insegna
    -0.43
     Houſe
    -0.43
     espressione
    -0.42
    Становништво
    -0.42
     PublicKey
    -0.42
     femininas
    -0.42
     femininos
    -0.42
    POSITIVE LOGITS
    contentLoaded
    0.49
     betweenstory
    0.43
    SBATCH
    0.43
     surla
    0.41
    sizeCache
    0.40
    成
    0.40
     بچ
    0.39
    Conver
    0.39
    mine
    0.39
    ंदीखरीदारी
    0.39
    Activations Density 0.131%

    No Known Activations