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. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 3709
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to service delivery and operational quality in a business context

    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
     препратки
    -0.93
     يتيمه
    -0.84
     BoxDecoration
    -0.83
     estekak
    -0.83
    ValueStyle
    -0.81
    featureID
    -0.80
    NameInMap
    -0.79
    delwed
    -0.78
     Мексичка
    -0.77
     AssemblyCompany
    -0.76
    POSITIVE LOGITS
     innovative
    1.06
     comprehensive
    1.05
     highly
    0.94
     robust
    0.89
     tailored
    0.81
     proven
    0.80
     effective
    0.79
     powerful
    0.79
     reliable
    0.77
     sophisticated
    0.77
    Activations Density 0.530%

    No Known Activations