© 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. 110240
    Prev
    Next
    INDEX
    Explanations

    words and phrases that convey the concept of movement or progress

    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
    Personensuche
    -0.64
    <_>
    -0.51
     Hex
    -0.51
    存于互联网档案馆
    -0.50
     IBOutlet
    -0.49
     /*#__
    -0.49
    viking
    -0.49
    Slf
    -0.47
     estekak
    -0.47
    jooq
    -0.47
    POSITIVE LOGITS
     considérons
    0.35
    Siehe
    0.33
    MongoClient
    0.32
     gratuites
    0.32
     отношения
    0.31
    colage
    0.30
    Literally
    0.29
    Outside
    0.28
    UnsafeEnabled
    0.28
     jardín
    0.28
    Activations Density 0.007%

    No Known Activations