© 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. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5419
    Prev
    Next
    INDEX
    Explanations

    technological and scientific terminology related to networks and layers in computational systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     désolés
    -0.55
    ]")]
    -0.54
     snippetHide
    -0.47
    SpringBootTest
    -0.46
    rungsseite
    -0.45
     useParams
    -0.44
    WaitGroup
    -0.44
     AssemblyCompany
    -0.43
    scriptId
    -0.41
    曖昧さ回避
    -0.39
    POSITIVE LOGITS
     layer
    3.53
     layers
    3.38
     Layer
    3.09
     Layers
    2.98
    layer
    2.95
    Layer
    2.91
     LAYER
    2.80
    layers
    2.69
    Layers
    2.63
    LAYER
    2.48
    Activations Density 1.325%

    No Known Activations