© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 5761
    Prev
    Next
    INDEX
    Explanations

    technical terms and variations related to descriptors in coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -1.07
    \{\\
    -0.99
    HasForeignKey
    -0.98
     contextLoads
    -0.96
    ArgsConstructor
    -0.96
    NUMX
    -0.96
    Skocz
    -0.95
     MainAxisSize
    -0.93
     MonoBehaviour
    -0.93
    AndroidJUnit
    -0.91
    POSITIVE LOGITS
    Descriptor
    2.25
    descriptor
    2.10
     Descriptor
    1.82
     descriptor
    1.74
    Descriptors
    1.65
    DESCRIPTOR
    1.32
     descriptors
    1.29
    getDescriptor
    1.25
    descriptors
    1.22
    FieldDescriptor
    1.15
    Activations Density 0.015%

    No Known Activations